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

    Neuronpedia

    INDEX
    Explanations

    条

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ინდ
    -0.09
     underwent
    -0.08
    datas
    -0.08
     earthy
    -0.08
    usses
    -0.08
    അ
    -0.08
     undergo
    -0.08
    ætter
    -0.08
     ошондой
    -0.07
    Soňky
    -0.07
    POSITIVE LOGITS
     Connecting
    0.08
     eigener
    0.08
     eigene
    0.08
     ومع
    0.07
     sarili
    0.07
     komentar
    0.07
     dolph
    0.07
     무료
    0.07
     propios
    0.07
     próprios
    0.07
    Act Density 0.000%

    No Known Activations