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

    Neuronpedia

    INDEX
    Explanations

    only parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    푞
    0.57
    Как
    0.54
    ాలు
    0.51
     rufis
    0.51
     brag
    0.50
     rapporter
    0.50
     berichten
    0.50
    ifal
    0.50
    SrvGroup
    0.50
     способности
    0.48
    POSITIVE LOGITS
    0.44
    </u>
    0.43
     Realms
    0.41
     الثلاث
    0.40
    su
    0.38
     Rated
    0.38
    EM
    0.36
    wil
    0.36
     Penguins
    0.36
     مداخل
    0.36
    Act Density 0.006%

    No Known Activations