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

    Neuronpedia

    INDEX
    Explanations

    pi or π

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bul
    0.87
    ロナ
    0.79
    仓
    0.79
     Baer
    0.79
     বাঙ্গ
    0.77
    Alic
    0.76
     韓国
    0.75
     Dent
    0.75
     Kaye
    0.74
    韩国
    0.73
    POSITIVE LOGITS
     pi
    3.50
     Pi
    3.49
    pi
    3.31
    Pi
    3.30
     PI
    3.16
    π
    3.04
     π
    3.03
     pie
    2.92
    PI
    2.86
     Pie
    2.83
    Act Density 0.057%

    No Known Activations