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

    Neuronpedia

    INDEX
    Explanations

    out of the way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infrared
    -0.07
    CEL
    -0.07
    ляд
    -0.07
    Před
    -0.07
     Plzeň
    -0.06
     Nikol
    -0.06
     blasph
    -0.06
     bic
    -0.06
    čemž
    -0.06
    JKLMNOP
    -0.06
    POSITIVE LOGITS
     leaderboard
    0.06
    .Models
    0.06
    (item
    0.06
    AVIS
    0.06
    .paths
    0.06
     thieves
    0.06
     each
    0.06
     records
    0.06
    !!)↵
    0.06
     dishwasher
    0.06
    Act Density 0.011%

    No Known Activations