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

    Neuronpedia

    INDEX
    Explanations

    package

    np_max-act · gemini-2.0-flash

    The neuron activates on the “package” keyword in code, i.e. it detects package declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    امل
    -0.07
    zier
    -0.06
    ünst
    -0.06
    _sub
    -0.06
     né
    -0.06
     Ning
    -0.06
    volent
    -0.06
    .POST
    -0.06
     burn
    -0.06
    かる
    -0.06
    POSITIVE LOGITS
     الاتحاد
    0.06
    <TEntity
    0.06
    uchsia
    0.06
     ;;↵
    0.06
    agem
    0.06
    ोख
    0.06
     Restaurants
    0.06
    ничес
    0.06
     '{"
    0.06
     timedelta
    0.06
    Act Density 0.002%

    No Known Activations