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

    Neuronpedia

    INDEX
    Explanations

    recipe instructions, dietary options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.80
    លើ
    0.74
    وص
    0.73
    迎接
    0.73
    णा
    0.73
     givenChar
    0.73
    adura
    0.72
    ieken
    0.72
    annten
    0.71
     sommeil
    0.71
    POSITIVE LOGITS
     Toshiba
    0.86
     Alibaba
    0.81
     Gazprom
    0.80
     Дэ
    0.80
     Эль
    0.78
     Adidas
    0.78
     Palladium
    0.77
     EN
    0.76
    nos
    0.76
     PUBG
    0.76
    Act Density 0.001%

    No Known Activations