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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xác
    -0.07
     Jos
    -0.07
     Fernandez
    -0.07
    เด
    -0.07
    .Top
    -0.06
    .Theme
    -0.06
    鞨
    -0.06
    От
    -0.06
    (grid
    -0.06
    .center
    -0.06
    POSITIVE LOGITS
     wouldn
    0.07
    roken
    0.07
    ullen
    0.07
     따른
    0.07
     WithEvents
    0.06
    平方
    0.06
    .splitext
    0.06
    Ｙ
    0.06
    ienen
    0.06
     Platt
    0.06
    Act Density 0.009%

    No Known Activations