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

    Neuronpedia

    INDEX
    Explanations

    integers and related prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    원은
    0.41
     অমিত
    0.39
    ház
    0.38
    都
    0.38
    лете
    0.37
    원이
    0.37
     علیکم
    0.37
    হাসিক
    0.37
     obwohl
    0.37
    山本
    0.37
    POSITIVE LOGITS
    Int
    0.75
     Int
    0.75
    INT
    0.60
    इंट
    0.60
     INT
    0.54
     Intra
    0.54
    it
    0.53
    ints
    0.53
    ToInt
    0.53
    entionally
    0.52
    Act Density 0.049%

    No Known Activations