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

    Neuronpedia

    INDEX
    Explanations

    foreign language or medical abbreviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ამართ
    0.45
    🖍
    0.41
     страница
    0.39
     Мол
    0.38
    ಂಭ
    0.37
    (.*
    0.37
    ्व
    0.37
    琍
    0.36
     kore
    0.35
    garakan
    0.35
    POSITIVE LOGITS
     thứ
    0.39
     rued
    0.38
     će
    0.38
     ऊंची
    0.38
     rues
    0.37
     третье
    0.37
    躡
    0.37
     uš
    0.36
     üçüncü
    0.35
    )."
    0.35
    Act Density 0.001%

    No Known Activations