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

    Neuronpedia

    INDEX
    Explanations

    f followed by "

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    1.71
    ️⃣
    1.41
    an
    1.38
    err
    1.17
    ^{*},
    1.17
    are
    1.16
    ir
    1.15
    ern
    1.15
    ль
    1.14
    ﻭ
    1.13
    POSITIVE LOGITS
    Мар
    1.43
    Ма
    1.32
    Ме
    1.25
    ୍ୟ
    1.23
    লায়
    1.21
     बड़े
    1.20
    Му
    1.16
     Recognize
    1.16
    те
    1.16
    aine
    1.13
    Act Density 0.211%

    No Known Activations