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

    Neuronpedia

    INDEX
    Explanations

    percentages and interest rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mille
    0.52
     thousand
    0.50
    thousand
    0.43
    henes
    0.42
     mart
    0.40
    %、
    0.40
     Martyrs
    0.40
    øy
    0.39
    ině
    0.38
     tisu
    0.38
    POSITIVE LOGITS
    юза
    0.41
     подгото
    0.38
     কুম
    0.38
    शा
    0.37
    Ӏ
    0.36
     Businesses
    0.36
     Bern
    0.35
     მონ
    0.34
     চতু
    0.33
     जिनसे
    0.33
    Act Density 0.002%

    No Known Activations