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

    Neuronpedia

    INDEX
    Explanations

    std

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TOUR
    -0.07
    есть
    -0.07
    cover
    -0.07
    -expression
    -0.07
    更加
    -0.07
     avalanche
    -0.06
    .cover
    -0.06
     employed
    -0.06
     glam
    -0.06
     vận
    -0.06
    POSITIVE LOGITS
     std
    0.09
    Std
    0.09
    .Std
    0.08
     Std
    0.08
    std
    0.07
    Todd
    0.07
     edu
    0.07
    _STD
    0.07
     fft
    0.07
    .preprocessing
    0.06
    Act Density 0.003%

    No Known Activations