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

    Neuronpedia

    INDEX
    Explanations

    large numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zeich
    1.61
     Css
    1.61
     Highlights
    1.58
    Highlights
    1.57
    룹
    1.56
    vorschau
    1.55
     рады
    1.55
     ena
    1.50
    тический
    1.49
    лся
    1.49
    POSITIVE LOGITS
     billion
    2.44
     trillion
    2.26
     million
    2.21
    billion
    2.00
     milliards
    1.96
     bilhões
    1.93
     billions
    1.81
     trillions
    1.78
     milhões
    1.68
     thousand
    1.67
    Act Density 0.142%

    No Known Activations