Typo

public/index.html

@@ -261,7 +261,7 @@ <h2 id="looking-at-a-single-image">Looking at a Single Image</h2>
     This is similar to Grad-CAM <d-cite key="selvaraju2016grad"></d-cite>, but without the spatial averaging of the gradient.
     Instead, we reduce noise in the gradient by using a continuous relaxation of the gradient for max pooling in computing the gradient (as in <d-cite key="olah2018building"></d-cite>).
     (A detailed reference implementation can be found in <a href="https://colab.research.google.com/github/tensorflow/lucid/blob/master/notebooks/building-blocks/AttrSpatial.ipynb">this notebook</a>.)
-    The attribution shown for cells in the activaiton atlas is the average of attribution vectors for activations in that cell.
+    The attribution shown for cells in the activation atlas is the average of attribution vectors for activations in that cell.
   </p>
 
   <p>