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

    Neuronpedia

    INDEX
    Explanations

    unless you have a compelling reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۵
    1.69
    ט
    1.63
    ﺮ
    1.57
    ﻄ
    1.54
    粹
    1.48
    ৩
    1.47
    谢
    1.44
    OOL
    1.41
     StringIO
    1.40
    onacci
    1.39
    POSITIVE LOGITS
    с
    2.00
     παιδιά
    1.75
    ра
    1.69
    ن
    1.68
     нем
    1.66
    jangan
    1.61
    не
    1.57
    ための
    1.55
     গেলে
    1.55
    н
    1.53
    Act Density 0.006%

    No Known Activations