"Neurons that fire together wire together"?
From TensorFlow homepage: "Next, the network is asked to solve a problem, which it attempts to do over and over, each time strengthening the connections that lead to success and diminishing those that lead to failure."
Are you looking for more technical details or an abstract concept?
After reading more materials I realized that it is just an indicator of the input(eg maybe a probability) and the next layer knows how to deal with it.
We're a place where coders share, stay up-to-date and grow their careers.
We strive for transparency and don't collect excess data.