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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ตรง
    -0.07
     моя
    -0.06
    //================================================================================
    -0.06
    _DAY
    -0.06
     ranges
    -0.06
    (stats
    -0.06
    .keras
    -0.06
    [color
    -0.06
    죄
    -0.06
     Systems
    -0.06
    POSITIVE LOGITS
    265
    0.07
     іншого
    0.07
    489
    0.06
     suicidal
    0.06
     Вар
    0.06
    161
    0.06
     номер
    0.06
    ジョ
    0.06
     ať
    0.06
     若
    0.06
    Act Density 0.000%

    No Known Activations