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

    Neuronpedia

    INDEX
    Explanations

    for some reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alan
    1.14
    1.11
    ीय
    1.11
    1.10
     pakai
    1.08
    1.06
    slag
    1.06
    шибка
    1.05
    1.04
    <0x1D>
    1.03
    POSITIVE LOGITS
    뵙
    1.28
    物的
    1.23
    на
    1.22
     somew
    1.20
    𝑎
    1.16
    ל
    1.14
    ا
    1.11
     sizeof
    1.10
    ্স
    1.08
     noção
    1.06
    Act Density 0.030%

    No Known Activations