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

    Neuronpedia

    INDEX
    Explanations

    source

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of the token “source,” i.e. references to source‐code files or directories.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Barbie
    -0.07
    .getBoolean
    -0.06
    _IS
    -0.06
     прок
    -0.06
    _busy
    -0.06
    『
    -0.06
     cinnamon
    -0.06
     WM
    -0.06
     AlertDialog
    -0.06
    获得
    -0.06
    POSITIVE LOGITS
     shocking
    0.07
    unal
    0.07
    enschaft
    0.06
    -origin
    0.06
    ensch
    0.06
    OR
    0.06
     replicate
    0.06
    ors
    0.06
    MAIN
    0.06
     अच
    0.06
    Act Density 0.010%

    No Known Activations