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

    Neuronpedia

    INDEX
    Explanations

    Enhancements and advancements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    网络
    -0.07
    <num
    -0.06
    .writeInt
    -0.06
     مدت
    -0.06
     lasted
    -0.06
    .broadcast
    -0.06
     participate
    -0.06
     Nashville
    -0.06
    prices
    -0.06
    Prices
    -0.06
    POSITIVE LOGITS
     rom
    0.06
     nervous
    0.06
    ==↵
    0.06
     roz
    0.06
     liberal
    0.06
    rası
    0.06
     cran
    0.06
     Mail
    0.06
    Help
    0.06
     misery
    0.06
    Act Density 0.111%

    No Known Activations