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

    Neuronpedia

    INDEX
    Explanations

    Foreign words/abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sampler
    -0.07
    刻苦
    -0.07
     людей
    -0.07
     לוקח
    -0.07
    (null
    -0.07
    ᨵ
    -0.07
     beginner
    -0.07
    @Api
    -0.07
     Samar
    -0.07
     toxic
    -0.07
    POSITIVE LOGITS
    Sys
    0.07
    eld
    0.07
    税务局
    0.07
    ITU
    0.07
    _Grid
    0.07
    WS
    0.07
    razione
    0.07
     Throws
    0.07
    ורה
    0.07
    を持
    0.06
    Act Density 0.037%

    No Known Activations