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

    Neuronpedia

    INDEX
    Explanations

    split screen, yell, dies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tentang
    0.46
    ی
    0.44
    면
    0.44
    heure
    0.43
     பக்கம்
    0.42
    lez
    0.42
     Với
    0.42
    헝
    0.42
    endering
    0.41
    洺
    0.41
    POSITIVE LOGITS
    ס
    0.45
    ുന്നു
    0.45
    ബന്ധ
    0.43
     egos
    0.43
     아니라
    0.43
     triv
    0.42
     डूब
    0.42
     ഉണ്ട്
    0.42
     толькі
    0.42
     to
    0.41
    Act Density 0.002%

    No Known Activations