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

    Neuronpedia

    INDEX
    Explanations

    options or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     製品
    0.44
    产品的
    0.43
     ఉత్ప
    0.42
     prodotti
    0.42
     시장
    0.41
    熱
    0.41
     ಉತ್ಪನ್ನ
    0.41
    產品
    0.41
    mittag
    0.41
     viscose
    0.40
    POSITIVE LOGITS
    หรือ
    0.45
     or
    0.43
     yoki
    0.42
     unless
    0.42
     veya
    0.42
     sayısı
    0.41
     hoặc
    0.41
     preference
    0.40
     they
    0.40
     fatally
    0.40
    Act Density 0.000%

    No Known Activations