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

    Neuronpedia

    INDEX
    Explanations

    Unusual proper nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Assembly
    -0.07
     Skywalker
    -0.07
     Ful
    -0.07
     flying
    -0.07
    ...")↵
    -0.06
    qrstuvwxyz
    -0.06
    Bat
    -0.06
    .WebElement
    -0.06
    Ingredient
    -0.06
     legalization
    -0.06
    POSITIVE LOGITS
    TION
    0.07
    ‐‐
    0.07
    prix
    0.07
    distinct
    0.07
     gp
    0.07
    _Inter
    0.07
     і
    0.07
    оні
    0.06
    _def
    0.06
    dispose
    0.06
    Act Density 0.019%

    No Known Activations