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

    Neuronpedia

    INDEX
    Explanations

    gender

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rubbed
    -0.08
     Maths
    -0.07
    际
    -0.06
    _has
    -0.06
     Builds
    -0.06
     zenith
    -0.06
     เ�
    -0.06
     perk
    -0.06
     Put
    -0.06
    .hy
    -0.06
    POSITIVE LOGITS
     다양한
    0.08
    گاه
    0.07
     BOOL
    0.07
    iverse
    0.07
     handicap
    0.07
     mainly
    0.07
     realistically
    0.06
    映画
    0.06
    Honestly
    0.06
    чів
    0.06
    Act Density 0.023%

    No Known Activations