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

    Neuronpedia

    INDEX
    Explanations

    crossing arms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     법칙
    0.47
     unambiguously
    0.43
    忡
    0.42
     अपेक्षित
    0.41
     क्रमशः
    0.41
     Sohn
    0.40
     ¿
    0.40
    ळ्यात
    0.40
     cả
    0.40
     ভূমিক
    0.40
    POSITIVE LOGITS
     avantaj
    0.45
    方式
    0.43
     way
    0.43
     realizados
    0.43
     exercitation
    0.42
     Probab
    0.42
     popularity
    0.41
    popularity
    0.41
    素晴らしい
    0.41
     preferring
    0.40
    Act Density 0.001%

    No Known Activations