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

    Neuronpedia

    INDEX
    Explanations

    __

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CEED
    -0.07
    qb
    -0.07
    енным
    -0.07
     yaptığ
    -0.06
     Kaplan
    -0.06
    pur
    -0.06
    .Bold
    -0.06
    338
    -0.06
    گي
    -0.06
    parated
    -0.06
    POSITIVE LOGITS
    หล
    0.07
     Theresa
    0.07
     wrappers
    0.07
    River
    0.06
    tempt
    0.06
    Apis
    0.06
    trade
    0.06
    /todo
    0.06
     tout
    0.06
    로서
    0.06
    Act Density 0.003%

    No Known Activations