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

    Neuronpedia

    INDEX
    Explanations

    purpose or consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sozial
    0.44
     purely
    0.41
    主に
    0.41
     jedynie
    0.41
     মূলত
    0.41
     Whereas
    0.39
     adlı
    0.39
     lediglich
    0.38
     नामक
    0.37
     Porém
    0.37
    POSITIVE LOGITS
     ताकि
    1.25
     تاکہ
    1.16
     lest
    1.10
    以免
    1.10
     чтобы
    1.05
     zodat
    1.02
     щоб
    0.99
     ώστε
    0.99
     כדי
    0.96
     যাতে
    0.95
    Act Density 0.013%

    No Known Activations