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

    Neuronpedia

    INDEX
    Explanations

    code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    핞
    0.81
    氇
    0.72
    дям
    0.71
    ድግዳ
    0.70
    いますが
    0.68
     pavattati
    0.68
    プレイヤー
    0.68
    います
    0.67
     स्वचालित
    0.67
     这
    0.66
    POSITIVE LOGITS
    u
    1.32
    a
    1.18
    ar
    1.09
    ла
    1.07
    ون
    1.05
    い
    1.04
    ли
    1.02
    ı
    1.02
    ة
    1.02
    ب
    1.01
    Act Density 0.301%

    No Known Activations