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

    Neuronpedia

    INDEX
    Explanations

    indulge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nell
    0.90
    ४
    0.84
    ları
    0.82
    larında
    0.82
     is
    0.81
    lands
    0.80
     berpikir
    0.76
    land
    0.75
    board
    0.74
    ५
    0.73
    POSITIVE LOGITS
    ك
    1.20
    ש
    1.09
    ن
    1.02
    ль
    0.98
    то
    0.93
    сть
    0.89
    ח
    0.86
    ",
    0.83
    л
    0.81
    ক
    0.81
    Act Density 0.001%

    No Known Activations