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

    Neuronpedia

    INDEX
    Explanations

    docstring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بندی
    1.06
    Cardiac
    1.05
     Clauses
    1.00
    থ্যা
    0.99
    ীর
    0.96
     widz
    0.96
     Discount
    0.95
    atial
    0.94
     pituitary
    0.94
    hotmail
    0.93
    POSITIVE LOGITS
    UMENTS
    1.59
    getElementById
    1.28
    umen
    1.26
    ᅠ
    1.22
     ఎమ్
    1.04
    umet
    1.04
     faptul
    1.03
    createElement
    1.02
    뱀
    1.00
    xygen
    0.99
    Act Density 0.049%

    No Known Activations