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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     winnings
    -0.10
     Betting
    -0.10
     mentale
    -0.09
    赌
    -0.09
     betting
    -0.09
     песни
    -0.09
     bettors
    -0.09
    的彩票
    -0.09
    ucleotide
    -0.09
     muts
    -0.08
    POSITIVE LOGITS
     декоратив
    0.12
     decorative
    0.12
     Decorative
    0.12
     recessed
    0.11
     embossed
    0.10
     masonry
    0.10
     junction
    0.10
     flange
    0.09
     furniture
    0.09
     stainless
    0.09
    Act Density 0.019%

    No Known Activations