Activation Function
An activation function is a mathematical step inside a neural network that adds nonlinearity to the model.
Category
AI Model Internals
These terms cover the math and architecture choices behind modern language models.
How to recognize this theme
Terms that describe what happens inside a model during inference.
In a daily board, this category groups terms by their shared role. Look for four cards that describe the same mechanism, risk area, or workflow rather than four words that merely sound similar.
Educational context
These entries are vocabulary notes for learning. They are not project endorsements, token recommendations, exchange rankings, or trading signals.
Tensor Parallelism
Tensor parallelism is a way to split large model computations across multiple devices at the same time.
Routing Layer
A routing layer directs inputs or requests to the part of a system best suited to handle them.
Mixture of Experts
A mixture of experts is a model design that uses multiple specialist networks and routes work to the right ones.