Fix incorrect code comment in neural_networks_tutorial (#3679)

The code example incorrectly labels the final linear layer as a
"Gaussian layer". However, `fc3` is a standard fully connected layer
(`nn.Linear(84, 10)`).

Updated the comment to "Fully connected layer" to avoid confusion.


cc @albanD @jbschlosser

Co-authored-by: Svetlana Karslioglu <svekars@meta.com>

Author: Sachapernak

beginner_source/blitz/neural_networks_tutorial.py

@@ -78,7 +78,7 @@ def forward(self, input):
         # Fully connected layer F6: (N, 120) Tensor input,
         # and outputs a (N, 84) Tensor, it uses RELU activation function
         f6 = F.relu(self.fc2(f5))
-        # Gaussian layer OUTPUT: (N, 84) Tensor input, and
+        # Fully connected layer OUTPUT: (N, 84) Tensor input, and
         # outputs a (N, 10) Tensor
         output = self.fc3(f6)
         return output