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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extremist
    -0.07
    ecute
    -0.07
     cuales
    -0.07
     roughly
    -0.07
     travels
    -0.07
    asse
    -0.06
    ,str
    -0.06
    creenshot
    -0.06
    _kwargs
    -0.06
    -pop
    -0.06
    POSITIVE LOGITS
     Outcome
    0.06
    踏
    0.06
     erotiske
    0.06
    GY
    0.06
    CTIONS
    0.06
     прям
    0.06
    pově
    0.06
    edics
    0.06
     rá
    0.06
     Tune
    0.06
    Act Density 0.044%

    No Known Activations