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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens, especially those used as identifiers or literal numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     田
    -0.07
    ”—
    -0.07
    人人
    -0.07
    general
    -0.06
    BIG
    -0.06
     یاد
    -0.06
     ін
    -0.06
    _params
    -0.06
    )—
    -0.06
     Param
    -0.06
    POSITIVE LOGITS
    .getD
    0.06
    <|python_tag|>
    0.06
    時代
    0.06
     velocities
    0.06
     replen
    0.06
    repository
    0.06
    lanır
    0.06
    edBy
    0.06
    ">

↵
    0.06
     coloc
    0.06
    Act Density 0.110%

    No Known Activations