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

    Neuronpedia

    INDEX
    Explanations

    the number 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forty
    1.52
     sixty
    1.51
     fifty
    1.45
     eighty
    1.44
     thirty
    1.43
     seventy
    1.39
     ninety
    1.36
     ten
    1.35
    thirty
    1.29
     Fifty
    1.29
    POSITIVE LOGITS
     ১
    2.44
     १
    2.27
    ১
    2.25
    １
    2.08
    1
    2.06
    One
    1.90
     One
    1.90
     ۱
    1.82
    ۱
    1.79
     ఒకటి
    1.77
    Act Density 1.522%

    No Known Activations