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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash

    This neuron fires on C++ class access specifier declarations, specifically the “public:” keyword.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    湯
    -0.07
    aha
    -0.06
    ereum
    -0.06
    北京
    -0.06
    SCRI
    -0.06
    NullOr
    -0.06
    avou
    -0.06
    emoth
    -0.06
    gang
    -0.06
    яж
    -0.06
    POSITIVE LOGITS
     attributes
    0.07
    -x
    0.06
    aptors
    0.06
    issue
    0.06
     objects
    0.06
     ;-
    0.06
     manic
    0.06
    <Color
    0.06
    葡
    0.06
    _j
    0.06
    Act Density 0.002%

    No Known Activations