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

    Neuronpedia

    INDEX
    Explanations

    private

    np_max-act · gemini-2.0-flash

    This neuron responds to tokens that introduce function or method definitions (e.g. keywords like “function,” “public,” “private,” or “static”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    iyan
    -0.06
    ケ
    -0.06
    ديث
    -0.06
    Skeleton
    -0.06
    _reporting
    -0.06
     CNN
    -0.06
    nih
    -0.06
    nd
    -0.05
     заверш
    -0.05
    ông
    -0.05
    POSITIVE LOGITS
    _ADV
    0.06
    imestone
    0.06
     BlockPos
    0.06
    _STORAGE
    0.06
    [col
    0.06
    StateException
    0.06
    (TEXT
    0.06
    Nova
    0.06
    _GU
    0.06
     contentType
    0.06
    Act Density 0.005%

    No Known Activations