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

    Neuronpedia

    INDEX
    Explanations

    large numbers and currency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    irts
    1.30
     다음에
    1.29
    族的
    1.28
    ramar
    1.25
    崎
    1.24
    apolis
    1.24
    gomery
    1.24
    тический
    1.23
    vist
    1.22
    vie
    1.21
    POSITIVE LOGITS
     billion
    1.60
    billion
    1.56
     million
    1.49
     Billion
    1.47
    €
    1.45
     USD
    1.42
     €
    1.40
     CHF
    1.40
     trillion
    1.40
     dollars
    1.38
    Act Density 0.215%

    No Known Activations