Extra tanh?

[dhzyingz]

In the backpropagation part, the first line code writes:

dtanh = softmaxOutput.diff(forward[len(forward)-1][2], y)

So it is activated then sent to softmax?
I guess for the last layer there is no need to add tanh before softmax? So the code would be:

dtanh = softmaxOutput.diff(forward[len(forward)-1][1], y)