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

    Neuronpedia

    INDEX
    Explanations

    processing actions/requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compat
    -0.08
    →
    -0.07
    _wait
    -0.07
    ste
    -0.07
    _circle
    -0.07
     tako
    -0.06
     Compact
    -0.06
    Qualifier
    -0.06
     graz
    -0.06
    elm
    -0.06
    POSITIVE LOGITS
     Forecast
    0.07
     پیامبر
    0.06
    기업
    0.06
     spreads
    0.06
     Федерации
    0.06
    릉
    0.06
     plantation
    0.06
    "Don
    0.06
    _roll
    0.06
    otel
    0.06
    Act Density 0.002%

    No Known Activations