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

    Neuronpedia

    INDEX
    Explanations

    numeric ranges and currencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     छठे
    0.91
    ৬
    0.91
     छठी
    0.83
    ၆
    0.83
     sixth
    0.83
    6
    0.77
     seventh
    0.77
     ৫ম
    0.77
     Sixth
    0.76
    irmeye
    0.76
    POSITIVE LOGITS
     Twenty
    1.28
     twenty
    1.17
     vingt
    1.14
    Twenty
    1.13
    twenty
    1.10
     ۲
    1.10
     двадцать
    1.04
    二十
    1.02
     nineteen
    1.02
    ២
    1.01
    Act Density 0.056%

    No Known Activations