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

    Neuronpedia

    INDEX
    Explanations

    Persian and Arabic words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mlijeka
    1.20
     børn
    1.11
     precludes
    1.06
     begyn
    1.04
     życia
    1.03
     mennes
    1.02
     simonsen
    1.02
     chiens
    1.00
     samoglas
    1.00
     attaques
    1.00
    POSITIVE LOGITS
     در
    1.22
     و
    1.20
     به
    1.18
     پ
    1.13
     د
    1.12
    1.09
     ر
    1.09
    پ
    1.09
     از
    1.07
     با
    1.03
    Act Density 0.002%

    No Known Activations