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

    Neuronpedia

    INDEX
    Explanations

    academic subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    1.89
    ς
    1.83
     altre
    1.78
    வும்
    1.77
    ed
    1.76
    sü
    1.69
    ্ত
    1.67
     обязательно
    1.64
    tains
    1.63
     olduğu
    1.62
    POSITIVE LOGITS
     marvel
    1.78
    ுள்ளார்
    1.67
    师
    1.65
    ियल
    1.59
    empres
    1.58
    ção
    1.58
     znači
    1.57
    োর
    1.56
    той
    1.55
    ﻢ
    1.52
    Act Density 0.519%

    No Known Activations