What does the clear() method exactly do?

[wagenaartje]

I'm trying to modify the layers in a perceptron with some code, by changing for example weights and biases. However when I activate the neural net with the same input again, I get the same output. Except if I use clear(), then magically I get another output after changing some biases and weigths.

I tried to look in the code, but I don't seem to understand what it's clearing. It's a perceptron right? No memory involved? Why does clear() change the output then?