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

    Neuronpedia

    INDEX
    Explanations

    Romance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    umento
    0.38
     탐
    0.38
     كند
    0.36
    тельно
    0.36
    nections
    0.35
     dokument
    0.35
     Explore
    0.35
    conciliation
    0.35
     例文帳に追加
    0.35
    дри
    0.35
    POSITIVE LOGITS
     propio
    0.47
    Gem
    0.41
     warms
    0.39
     toug
    0.39
    gem
    0.38
     próprio
    0.38
    Lyrics
    0.38
     amor
    0.38
     vitae
    0.38
     પ્રેમ
    0.38
    Act Density 0.018%

    No Known Activations