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

    Neuronpedia

    INDEX
    Explanations

    ra

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cost
    -0.07
    .MustCompile
    -0.07
    ご
    -0.06
    _stdout
    -0.06
    .list
    -0.06
     Anime
    -0.06
    ¨
    -0.06
     upgrading
    -0.06
    .people
    -0.06
    (Int
    -0.06
    POSITIVE LOGITS
     dří
    0.07
    ienda
    0.06
     clientele
    0.06
    inion
    0.06
    Base
    0.06
    canonical
    0.06
    -toast
    0.06
     Rockies
    0.06
    esan
    0.06
    .angular
    0.06
    Act Density 0.003%

    No Known Activations