Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code file paths

    np_max-act · gemini-2.0-flash

    This neuron fires on C/C++ `#include` tokens naming audio–signal‐processing header files (e.g. generator/Sine.h, fx/Delay.h, fx/Pitch.h).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	system
    -0.07
     crews
    -0.06
     Explorer
    -0.06
     duty
    -0.06
    _activate
    -0.06
     exports
    -0.06
     Copies
    -0.06
     awakened
    -0.06
     prefetch
    -0.06
     Stock
    -0.06
    POSITIVE LOGITS
    .er
    0.07
     khối
    0.07
    Normalized
    0.07
    чук
    0.06
     irr
    0.06
     besar
    0.06
    :↵↵↵
    0.06
    ي
    0.06
    ↵↵↵↵↵↵↵↵↵↵
    0.06
    Ne
    0.06
    Act Density 0.066%

    No Known Activations