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

    Neuronpedia

    INDEX
    Explanations

    large numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     była
    -2.08
     determinado
    -1.98
    ője
    -1.85
    鼉
    -1.75
    表達
    -1.73
    ssos
    -1.70
    "));
    -1.69
    ksesta
    -1.68
     ہے۔
    -1.66
    -1.66
    POSITIVE LOGITS
     —
    2.22
    people
    1.66
     где
    1.64
     что
    1.59
    you
    1.58
     куда
    1.58
     other
    1.57
     of
    1.57
    人也
    1.55
     самое
    1.54
    Act Density 0.006%

    No Known Activations