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

    Neuronpedia

    INDEX
    Explanations

    dish or dishes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dır
    1.00
    the
    0.97
    times
    0.89
     be
    0.86
    る
    0.86
    ม
    0.86
    ğı
    0.84
    to
    0.84
    ta
    0.84
     بانک
    0.83
    POSITIVE LOGITS
     Dishes
    1.20
     ﺍ
    1.13
     dishes
    1.09
    al
    1.03
     Григо
    1.02
     Dish
    0.99
    Dish
    0.97
     Ι
    0.96
    ﺍ
    0.95
    "
    0.94
    Act Density 0.008%

    No Known Activations