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
    外墙
    -0.08
     poll
    -0.07
    较强的
    -0.07
    ᡝ
    -0.07
    投标
    -0.06
     punctuation
    -0.06
     Supports
    -0.06
     birds
    -0.06
    emale
    -0.06
     Mes
    -0.06
    POSITIVE LOGITS
    ậy
    0.07
     tantra
    0.07
    _visited
    0.07
    _coeff
    0.07
    .Mutable
    0.07
    وال
    0.07
     חוזר
    0.07
    étude
    0.07
    itsu
    0.07
    ריות
    0.07
    Act Density 0.099%

    No Known Activations