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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     divul
    -0.08
     côt
    -0.07
    性格
    -0.07
    _DIG
    -0.07
    孜
    -0.07
     Css
    -0.07
     vaz
    -0.07
    消費
    -0.07
     emphasis
    -0.07
    فوز
    -0.07
    POSITIVE LOGITS
    .co
    0.07
     scooter
    0.07
     Folding
    0.07
    idable
    0.06
    mutable
    0.06
     właśnie
    0.06
     Stevens
    0.06
     multiplier
    0.06
    えて
    0.06
     blanco
    0.06
    Act Density 0.014%

    No Known Activations