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

    Neuronpedia

    INDEX
    Explanations

    large amount or range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     robust
    0.72
     more
    0.71
    simple
    0.71
     simple
    0.68
     meticulous
    0.67
    three
    0.66
     relatively
    0.65
    one
    0.65
     somewhat
    0.65
     prestigious
    0.65
    POSITIVE LOGITS
     amount
    1.43
     количество
    1.30
     Amount
    1.20
    amount
    1.16
     cantidad
    1.15
     aantal
    1.14
     quantidade
    1.12
     AMOUNT
    1.10
     кількість
    1.07
     Anzahl
    1.06
    Act Density 0.177%

    No Known Activations