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

    Neuronpedia

    INDEX
    Explanations

    Interested people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _in
    -0.07
    :params
    -0.07
    ء
    -0.07
    ность
    -0.07
    _D
    -0.06
     follows
    -0.06
     grips
    -0.06
    ﾝ
    -0.06
    ﯻ
    -0.06
     praying
    -0.06
    POSITIVE LOGITS
     המד
    0.07
    -rated
    0.07
    entionPolicy
    0.07
    再造
    0.07
    LEncoder
    0.07
     lith
    0.06
    cılı
    0.06
    abort
    0.06
     tweeted
    0.06
    信息公开
    0.06
    Act Density 0.123%

    No Known Activations