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

    Neuronpedia

    INDEX
    Explanations

    foreign words or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    0.48
    ските
    0.48
    тите
    0.45
     subv
    0.44
    _",
    0.44
     moreover
    0.43
     furthermore
    0.43
    ^+,
    0.43
     Balls
    0.43
     Order
    0.43
    POSITIVE LOGITS
     плат
    0.44
    鋃
    0.43
     потер
    0.40
    udades
    0.39
     storm
    0.39
     Cambio
    0.38
    钀
    0.38
    jours
    0.38
    ouring
    0.38
    hiqdev
    0.38
    Act Density 0.001%

    No Known Activations