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

    Neuronpedia

    INDEX
    Explanations

    notice and notification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    2.00
    نا
    1.88
    น่า
    1.84
    นิ
    1.78
    но
    1.77
    ک
    1.77
    ﺒ
    1.77
    لی
    1.73
    ますが
    1.71
    น
    1.70
    POSITIVE LOGITS
    '
    1.80
    th
    1.53
    ัก
    1.51
    ’
    1.47
    gger
    1.39
     blasted
    1.28
     acclaim
    1.28
     intently
    1.28
     dù
    1.27
    of
    1.26
    Act Density 0.091%

    No Known Activations