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

    Neuronpedia

    INDEX
    Explanations

    categories, types, or aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Adin
    0.52
    lá
    0.45
    йки
    0.45
    ći
    0.45
    في
    0.44
    uwe
    0.44
     अंशु
    0.43
     આધાર
    0.42
     Yoshida
    0.42
    Zag
    0.42
    POSITIVE LOGITS
    >,</
    0.49
     compounded
    0.43
    টর
    0.42
     soggetti
    0.41
    ərd
    0.40
     entities
    0.39
    選挙
    0.39
    ར་
    0.39
    ரா
    0.38
    লার
    0.38
    Act Density 0.003%

    No Known Activations