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

    Neuronpedia

    INDEX
    Explanations

    numerical magnitudes: million, billion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Words
    0.75
    Davis
    0.71
     посети
    0.70
    Seats
    0.69
     Urb
    0.68
    words
    0.68
     Вален
    0.67
     ()
    0.67
     Intervals
    0.66
     клетки
    0.66
    POSITIVE LOGITS
     million
    2.10
     billion
    2.03
     billions
    1.73
     millions
    1.68
    million
    1.65
     trillion
    1.51
     miliardi
    1.47
     Million
    1.46
     Millionen
    1.44
    billion
    1.44
    Act Density 0.313%

    No Known Activations