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

    Neuronpedia

    INDEX
    Explanations

    use and its contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ü
    0.84
    ä
    0.81
    that
    0.77
    í
    0.77
    w
    0.77
    r
    0.73
    ö
    0.73
    什麼
    0.71
    t
    0.71
    m
    0.71
    POSITIVE LOGITS
    行う
    0.62
     باشند
    0.61
    부에
    0.60
    OfInterest
    0.59
     raggi
    0.58
    ಗಾಗಿ
    0.58
    akha
    0.58
    u
    0.57
    の高い
    0.56
    ‌ی
    0.56
    Act Density 0.015%

    No Known Activations