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

    Neuronpedia

    INDEX
    Explanations

    cannot and will not fulfill your request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۱۳
    0.46
     ไม่
    0.46
    ∈
    0.43
    ປັນ
    0.43
    InProgress
    0.41
     Terima
    0.40
    ১৮
    0.40
    itej
    0.40
    gaxModule
    0.39
    ເປັນ
    0.39
    POSITIVE LOGITS
     снова
    0.41
     또한
    0.41
     microp
    0.38
    รัก
    0.37
     روی
    0.37
     রোগীর
    0.36
    所谓的
    0.35
     வெறும்
    0.35
    Reader
    0.35
    ровень
    0.34
    Act Density 0.071%

    No Known Activations