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

    Neuronpedia

    INDEX
    Explanations

    Valais, valleys, names, brands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     twos
    1.11
     barter
    1.05
     turnt
    1.04
    Stdout
    1.04
     взя
    1.02
     melamine
    1.02
     взял
    1.01
    RAchievement
    1.00
     Returning
    0.99
    𝓵
    0.98
    POSITIVE LOGITS
    場合
    1.33
    czyć
    1.09
    ير
    1.04
    ivating
    1.03
    ը
    1.01
    uesa
    0.99
    াপন
    0.99
    цю
    0.98
    これまで
    0.97
    т
    0.97
    Act Density 0.052%

    No Known Activations