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

    Neuronpedia

    INDEX
    Explanations

    importance on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    花园
    0.63
    alarını
    0.61
    瘓
    0.61
    masını
    0.59
     Algun
    0.59
     çıktı
    0.59
     Üniversitesi
    0.56
     görev
    0.56
     tartış
    0.55
     ayrı
    0.55
    POSITIVE LOGITS
    ・
    0.72
    ※
    0.71
    leqq
    0.70
     ・
    0.63
    〜
    0.61
    ＜
    0.60
    ｌ
    0.60
    ≒
    0.60
    ～
    0.59
    (=
    0.56
    Act Density 0.020%

    No Known Activations