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

    Neuronpedia

    INDEX
    Explanations

    dtype

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bo
    -0.07
    Wy
    -0.07
     такий
    -0.06
     Scatter
    -0.06
    _TO
    -0.06
     examination
    -0.06
    _sections
    -0.06
     Sho
    -0.06
     servis
    -0.06
     Zug
    -0.06
    POSITIVE LOGITS
    _transform
    0.07
    άν
    0.07
     course
    0.06
    宁
    0.06
    ียง
    0.06
    133
    0.06
    (dtype
    0.06
    .dtype
    0.06
     Mutable
    0.06
    .Size
    0.06
    Act Density 0.004%

    No Known Activations