Clarify meaning of 2D contours in Minuit.draw_mnmatrix (#927)

The method `Minuit.draw_mnmatrix` shows 2D contours that do not align
with the 1D intervals, which is ok. The keyword `cl` sets the confidence
level for the 1D intervals and 2D contours, according to Wilks' theorem,
the projections of the 2D contours are then wider than the 1D intervals.
The docstrings make this point more clear.

doc/reference.rst

@@ -27,11 +27,13 @@ These methods and properties you will probably use a lot:
     Minuit.fval
     Minuit.nfit
     Minuit.mnprofile
-    Minuit.draw_mnprofile
+    Minuit.mncontour
+    Minuit.visualize
+    Minuit.draw_mnmatrix
 
 
-Minuit
-------
+Main interface
+--------------
 
 .. autoclass:: Minuit
     :members:

src/iminuit/minuit.py

@@ -1916,7 +1916,11 @@ def mncontour(
         scan point. This scan produces a statistical confidence region according to the
         `profile likelihood method <https://en.wikipedia.org/wiki/Likelihood_function>`_
         with a confidence level `cl`, which is asymptotically equal to the coverage
-        probability of the confidence region.
+        probability of the confidence region according to `Wilks' theorem
+        <https://en.wikipedia.org/wiki/Wilks%27_theorem>`. Note that 1D projections of
+        the 2D confidence region are larger than 1D Minos intervals computed for the
+        same confidence level. This is not an error, but a consequence of Wilks'
+        theorem.
 
         The calculation is expensive since a numerical minimisation has to be performed
         at various points.
@@ -2085,8 +2089,12 @@ def draw_mnmatrix(
         This draws a matrix of Minos likelihood scans, meaning that the likelihood is
         minimized with respect to the parameters that are not scanned over. The diagonal
         cells of the matrix show the 1D scan, the off-diagonal cells show 2D scans for
-        all unique pairs of parameters. The 2D scans show confidence regions. See
-        :meth:`mncontour` for details on the interpretation of these regions.
+        all unique pairs of parameters.
+
+        The projected edges of the 2D contours do not align with the 1D intervals,
+        because of Wilks' theorem. The levels for 2D confidence regions are higher. For
+        more information on the interpretation of 2D confidence regions, see
+        :meth:`mncontour`.
 
         Parameters
         ----------