Simple version
A careful map of how a much bigger, more complex AI model routes its work internally.
In plain terms
Nemotron-3 Super has 120 billion parameters and a mixture-of-experts design that sends different parts of an answer to different sub-networks. We captured both the expert-routing decisions and the attention edges, and showed the map reproduces exactly across independent runs on the same machine.
Technical artifact
Canonical mixed-edge topology for a 120B hybrid model, 896 bounded edges across expert routing and attention, emitted under a determinism-gated admission rule.