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

    Neuronpedia

    INDEX
    Explanations

    words surrounded by asterisks or hyphens, and certain URLs and references, in STEM-related texts.

    oai_token-act-pair · gemini-2.0-flash

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +#+#
    -0.77
     Wallflower
    -0.72
    CloseOperation
    -0.69
    таратура
    -0.66
     DialogResult
    -0.65
    rolid
    -0.64
    bollah
    -0.63
    leyball
    -0.60
    XMLSchema
    -0.60
    riges
    -0.60
    POSITIVE LOGITS
    <bos>
    0.79
     CHAPITRE
    0.59
     चीज़ों
    0.53
    dientemente
    0.52
     Nacionales
    0.49
     Chapitre
    0.48
    Dữ
    0.48
     quæ
    0.48
     Consejo
    0.48
    bbene
    0.48
    Act Density 3.974%

    No Known Activations