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

    Neuronpedia

    INDEX
    Explanations

    require statement for libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ︹
    0.46
     الداله
    0.40
    pev
    0.40
    |}{
    0.40
    Larry
    0.40
    ([-
    0.39
    tvrt
    0.38
    Knight
    0.38
    def
    0.38
    sidenav
    0.38
    POSITIVE LOGITS
    tidyverse
    0.50
     bund
    0.43
    ggplot
    0.42
     krä
    0.42
     REQUI
    0.41
     ggplot
    0.40
    logger
    0.39
     priorit
    0.38
     Requ
    0.38
     cracking
    0.38
    Act Density 0.003%

    No Known Activations