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

    Neuronpedia

    INDEX
    Explanations

    reversing words or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     యొక్క
    1.11
    하였습니다
    1.07
     Honorable
    1.02
    っております
    0.97
     اون
    0.96
     উক্ত
    0.96
     हेतु
    0.95
    非常的
    0.95
     diatas
    0.94
     మరియు
    0.94
    POSITIVE LOGITS
    1.03
    0.96
     अफसरों
    0.89
    0.88
    cedures
    0.87
    ➊
    0.85
    耻
    0.85
    ेक्षा
    0.84
    0.84
     sólo
    0.84
    Act Density 0.008%

    No Known Activations