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

    Neuronpedia

    INDEX
    Explanations

    -b

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    桹
    -0.08
     Aristotle
    -0.07
    outfile
    -0.07
    取得以及
    -0.07
    中秋节
    -0.06
     Tinder
    -0.06
    validate
    -0.06
    )!=
    -0.06
    菲律
    -0.06
     polygon
    -0.06
    POSITIVE LOGITS
    ·
    0.07
     {
↵
↵
    0.07
    (pd
    0.07
     eas
    0.07
    وير
    0.07
    呃
    0.07
     vente
    0.07
    [b
    0.07
    ukes
    0.07
     Enjoy
    0.07
    Act Density 0.508%

    No Known Activations