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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    This neuron detects code identifier tokens (names of variables, types, methods, classes, etc.) across programming-language snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    DDS
    -0.08
    directive
    -0.07
     він
    -0.07
    quences
    -0.07
    qr
    -0.06
     Defensive
    -0.06
    being
    -0.06
    Britain
    -0.06
    avoid
    -0.06
    REEN
    -0.06
    POSITIVE LOGITS
     Ritch
    0.07
     ambiguous
    0.06
    ισμ
    0.06
    ン�
    0.06
    AML
    0.06
     français
    0.06
     Mish
    0.06
     الأد
    0.06
     Kı
    0.06
    ={[
    0.06
    Act Density 0.037%

    No Known Activations