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

    Neuronpedia

    INDEX
    Explanations

    version or name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ä
    2.30
     বসে
    2.23
    ä
    2.15
    います
    2.10
     sendiri
    2.06
     kne
    2.06
     dator
    2.05
    A
    2.04
    Спасибо
    2.04
    У
    2.04
    POSITIVE LOGITS
    এর
    3.36
    ––
    3.28
    _-
    3.15
    וה
    2.78
    ̀
    2.64
    &-
    2.63
    <0x80>
    2.53
    ्लादेश
    2.39
     $-$
    2.39
    –
    2.36
    Act Density 0.810%

    No Known Activations