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

    Neuronpedia

    INDEX
    Explanations

    lists, numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    2.36
    ため
    1.88
    ز
    1.80
    ة
    1.69
    客様
    1.66
    ции
    1.63
    い
    1.59
    ي
    1.59
    }";
    1.55
     Tetapi
    1.52
    POSITIVE LOGITS
    ной
    1.63
    ır
    1.45
    च्या
    1.43
    在
    1.41
    ik
    1.38
    在于
    1.37
    ée
    1.33
     chol
    1.29
    umé
    1.29
     রয়েছে
    1.26
    Act Density 0.121%

    No Known Activations