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

    Neuronpedia

    INDEX
    Explanations

    license or rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    1.98
    د
    1.75
    ли
    1.74
     הם
    1.68
    ب
    1.65
    t
    1.61
    ۵
    1.61
    ت
    1.60
    тэй
    1.58
    the
    1.56
    POSITIVE LOGITS
    ра
    1.91
    ри
    1.59
    ן
    1.49
    }$.
    1.48
    *.
    1.46
    岁月
    1.43
    ous
    1.42
    }$
    1.39
    đer
    1.38
    的工作
    1.36
    Act Density 0.000%

    No Known Activations