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

    Neuronpedia

    INDEX
    Explanations

    urls and code characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الشر
    0.57
     الجمهور
    0.55
     الس
    0.54
     ست
    0.54
     الر
    0.53
    =.
    0.53
     Librarian
    0.53
     الل
    0.53
     जीत
    0.52
    পুরুষ
    0.52
    POSITIVE LOGITS
    ı
    0.77
    на
    0.76
    क
    0.71
    uning
    0.71
    ಾ
    0.69
    ク
    0.67
    та
    0.66
    at
    0.65
    ู
    0.64
    ন
    0.64
    Act Density 0.137%

    No Known Activations