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

    Neuronpedia

    INDEX
    Explanations

    Slavic languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    För
    0.57
     Функ
    0.55
     Sử
    0.55
     Vý
    0.54
    Produto
    0.53
    Datei
    0.53
    Pentru
    0.53
     alkalmaz
    0.53
    К
    0.53
    Prz
    0.52
    POSITIVE LOGITS
     those
    0.48
     to
    0.41
     Those
    0.40
    那些
    0.38
     pot
    0.36
     whole
    0.35
     never
    0.33
     neither
    0.33
     tot
    0.33
     already
    0.32
    Act Density 0.013%

    No Known Activations