What is the definition of a “rectified conv feature map” in a convolutional neural network mentioned in the paper of "visual explaination"?

Question

I have read the answer of the question

What is the definition of a “feature map” (aka “activation map”) in a convolutional neural network?

But I don't think that it is same as what I want. I also try to search it on google but I was not able to find that exact thing anywhere.

I have come across this word in this paper: Grad-CAM:Visual Explanations from Deep Networks via Gradient-based Localization It is used after CNN in forward propogation.

Answer 1

I'm pretty sure it just means a feature map produced by relu (rectified linear) units.