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

    Neuronpedia

    INDEX
    Explanations

    why is it asked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    లుగు
    0.41
     новом
    0.38
    が良い
    0.37
     خبرنگ
    0.37
    卷
    0.36
     planar
    0.36
     νέα
    0.36
     comenzó
    0.35
     industrious
    0.35
    planar
    0.35
    POSITIVE LOGITS
    どちら
    0.45
     Enabling
    0.44
     empowering
    0.42
     :");
    0.42
    ില്ല
    0.41
     категорії
    0.41
    pem
    0.41
    หรือไม่
    0.41
     ultimate
    0.40
     गोवा
    0.40
    Act Density 0.001%

    No Known Activations