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

    Neuronpedia

    INDEX
    Explanations

    select -- or _

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻣ
    1.71
    goers
    1.70
    い
    1.69
    та
    1.66
    ك
    1.66
    ﺳ
    1.66
    ли
    1.61
    ﺷ
    1.60
    ﻛ
    1.55
    дин
    1.49
    POSITIVE LOGITS
    pués
    1.34
    more
    1.34
    ‍♀️
    1.33
    ‍♀
    1.32
    maßen
    1.32
    ‍♂️
    1.30
    了很多
    1.29
    AN
    1.28
    టానికి
    1.27
    ು
    1.27
    Act Density 0.001%

    No Known Activations