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

    Neuronpedia

    INDEX
    Explanations

    plea glee free

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    रुख
    0.80
    extent
    0.80
    ilience
    0.79
    rma
    0.77
    dosage
    0.73
    Extent
    0.73
     lensa
    0.72
     фильмов
    0.72
    <unused1087>
    0.71
    蝕
    0.70
    POSITIVE LOGITS
     réussi
    0.81
     terci
    0.80
     sheep
    0.74
    Er
    0.73
    苅
    0.73
     col
    0.73
    fre
    0.73
     Ч
    0.72
     ಗ್ರಾ
    0.72
     Peru
    0.72
    Act Density 0.001%

    No Known Activations