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

    Neuronpedia

    INDEX
    Explanations

    power dynamics in your life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تين
    0.44
    كس
    0.42
    讯
    0.41
     анали
    0.39
    シップ
    0.39
    دين
    0.39
    實驗
    0.38
     antiv
    0.38
    }{-
    0.38
    }}-\
    0.37
    POSITIVE LOGITS
     when
    0.50
     dreamy
    0.48
     ਉਸ
    0.48
     khi
    0.47
     når
    0.47
     la
    0.47
     salida
    0.46
     quando
    0.46
     மீண்டும்
    0.46
     جوئے
    0.46
    Act Density 0.003%

    No Known Activations