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

    Neuronpedia

    INDEX
    Explanations

    .sample .example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的关注
    -0.07
    无助
    -0.07
    Counts
    -0.07
     rms
    -0.07
     cutoff
    -0.07
     модель
    -0.07
    xious
    -0.06
    scanf
    -0.06
    attempt
    -0.06
    jection
    -0.06
    POSITIVE LOGITS
    ᅥ
    0.08
    雕
    0.08
    从小就
    0.07
    :E
    0.07
    画
    0.07
    ERICA
    0.07
    黑客
    0.07
    家装
    0.07
    鸪
    0.06
     drastic
    0.06
    Act Density 0.043%

    No Known Activations