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

    Neuronpedia

    INDEX
    Explanations

    words starting with pi or pix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     विभागीय
    0.40
    }"]
    0.39
    fantastic
    0.39
    ﺸ
    0.39
    :'],
    0.38
     Ön
    0.38
    ැබ
    0.37
    ્લા
    0.37
    sinya
    0.37
    DomainMask
    0.37
    POSITIVE LOGITS
     PI
    0.83
     пі
    0.81
     пи
    0.80
     pi
    0.77
     ピ
    0.75
     Pik
    0.71
    PI
    0.70
     Пи
    0.70
     Pix
    0.68
     Пі
    0.68
    Act Density 0.054%

    No Known Activations