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

    Neuronpedia

    INDEX
    Explanations

    setting/settings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Vector
    -0.07
    ideal
    -0.06
    globals
    -0.06
     Cv
    -0.06
    .readdir
    -0.06
     Paz
    -0.06
     integration
    -0.06
    [Z
    -0.06
     Gespr
    -0.06
     feu
    -0.06
    POSITIVE LOGITS
    _recent
    0.08
    irtual
    0.08
    簿
    0.07
    꿨
    0.07
     killed
    0.07
    抹
    0.07
    流失
    0.07
    半
    0.07
     protector
    0.07
    xima
    0.07
    Act Density 0.015%

    No Known Activations