SESK: Stuff Everyone Should Know · sesk.info/ai-relu-max-zero
What does the ReLU activation return for an input x?
ReLU returns max(0, x).
- max(0, x) ✔
- 1 divided by x
- x squared
Why: Negative inputs become zero. Zero and positive inputs pass through unchanged, making ReLU simple and piecewise linear.
Huh, didn't know that: ReLU has slope 1 on its positive side and slope 0 on its negative side.
ReLU stays positive, but only when the input does.
Like this card?
References
Answer: max(0, x). Negative inputs become zero. Zero and positive inputs pass through unchanged, making ReLU simple and piecewise linear.
- Google Machine Learning Crash Course: Activation functions developers.google.com/machine-learning/crash-course/neural-networks/activation-functions
is greater than or equal to 0, return the input value.
Checked 2026-10-11.
Think this answer is wrong? Tap "Challenge this answer" on the card in the game and tell us why.
More stuff everyone should know
That's stuff everyone should know.