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

    Neuronpedia

    INDEX
    Explanations

    variants and alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    3.45
    an
    3.39
    er
    3.04
    arbe
    2.93
    脊
    2.84
    ्ञ
    2.80
    Просе
    2.77
    erche
    2.77
    र
    2.73
    oresis
    2.67
    POSITIVE LOGITS
    뀌
    3.09
    которые
    3.04
    स्थ्य
    3.02
     использования
    2.71
    это
    2.67
    ں
    2.67
    på
    2.67
    minded
    2.66
    ی
    2.65
    फारिश
    2.64
    Act Density 0.073%

    No Known Activations