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

    Neuronpedia

    INDEX
    Explanations

    Code/Data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     项
    -0.06
    的な
    -0.06
     later
    -0.06
    tier
    -0.06
    那么
    -0.06
    captures
    -0.06
     최
    -0.06
    实施
    -0.06
    ửi
    -0.06
     Swe
    -0.06
    POSITIVE LOGITS
    _WIFI
    0.09
     vans
    0.07
     synd
    0.07
     Marxist
    0.07
    _WARNINGS
    0.07
    /maps
    0.07
    GameState
    0.06
     GP
    0.06
     فوت
    0.06
    rail
    0.06
    Act Density 8.165%

    No Known Activations