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

    Neuronpedia

    INDEX
    Explanations

    viagra and Shakespeare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    1.07
    с
    1.02
    f
    0.84
    的就是
    0.80
    ب
    0.79
    ور
    0.79
    ش
    0.75
    **
    0.75
    OS
    0.71
     மாறிய
    0.71
    POSITIVE LOGITS
    ни
    0.94
    ка
    0.83
    する
    0.81
     copyrights
    0.81
    ัน
    0.79
    ADIAN
    0.78
     Иң
    0.77
    ilte
    0.77
    ટ્સ
    0.76
    ים
    0.74
    Act Density 0.001%

    No Known Activations