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

    Neuronpedia

    INDEX
    Explanations

    anic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    欸
    -0.07
    NSNumber
    -0.07
    付费
    -0.07
    EMAIL
    -0.07
    _equalTo
    -0.07
    灿
    -0.07
    条评论
    -0.07
     |=
    -0.07
    相伴
    -0.07
    导师
    -0.07
    POSITIVE LOGITS
    SY
    0.07
    ował
    0.07
     prisons
    0.07
    lowest
    0.07
    ギ
    0.06
     modulation
    0.06
     Machine
    0.06
    ından
    0.06
    判决
    0.06
     slashing
    0.06
    Act Density 0.000%

    No Known Activations