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

    Neuronpedia

    INDEX
    Explanations

    thousand suns bleed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    2.16
    ت
    2.15
    ма
    2.06
    я
    1.89
    as
    1.86
    ﻤ
    1.82
    tiba
    1.81
    ufig
    1.79
    да
    1.76
    ط
    1.76
    POSITIVE LOGITS
    ر
    1.92
     неде
    1.90
    ों
    1.87
    ^{-}$
    1.87
     ova
    1.83
     σκ
    1.80
    ு
    1.79
     embroidery
    1.78
     отра
    1.78
     necessarily
    1.77
    Act Density 0.000%

    No Known Activations