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

    Neuronpedia

    INDEX
    Explanations

    component scores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     విజయ
    0.58
     మొదటి
    0.55
     Kana
    0.51
    ItemLayout
    0.49
    ToBase
    0.49
     Дей
    0.46
     প্রতিনি
    0.45
     ежедневно
    0.45
    ien
    0.44
     ロー
    0.44
    POSITIVE LOGITS
    的重要
    0.52
    艾
    0.52
    딩
    0.50
    。
    0.50
    به
    0.48
    ध
    0.47
    spaces
    0.47
    ।
    0.46
    有什么
    0.46
    重要
    0.46
    Act Density 0.000%

    No Known Activations