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

    Neuronpedia

    INDEX
    Explanations

    imaginary unit and indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䡛
    0.72
    ະລ
    0.68
     Menz
    0.65
    熱
    0.63
     cunt
    0.63
     чем
    0.63
    brus
    0.62
     وط
    0.62
    พลัง
    0.62
    غم
    0.62
    POSITIVE LOGITS
     i
    2.76
     İ
    2.20
    i
    2.15
    ｉ
    1.94
     í
    1.91
    イ
    1.87
    𝑖
    1.78
     イ
    1.75
     இ
    1.74
     아이
    1.74
    Act Density 1.543%

    No Known Activations