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

    Neuronpedia

    INDEX
    Explanations

    Cato Institute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    พรรณ
    -0.08
     Başkanlığı
    -0.07
    configuration
    -0.07
    勐
    -0.07
    �
    -0.06
    읭
    -0.06
    inne
    -0.06
     mois
    -0.06
    גלגל
    -0.06
    骍
    -0.06
    POSITIVE LOGITS
    EMON
    0.07
     שכל
    0.07
    سفير
    0.07
    _support
    0.07
    tahun
    0.07
     Phantom
    0.07
    ------
    0.07
    elson
    0.07
    不必
    0.06
    uran
    0.06
    Act Density 0.009%

    No Known Activations