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

    Neuronpedia

    INDEX
    Explanations

    URLs, paths, and namespaces

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     esternos
    -0.76
    IntoConstraints
    -0.74
     ModelExpression
    -0.73
     pleaſure
    -0.69
    StructEnd
    -0.69
     tartalomajánló
    -0.69
     becauſe
    -0.68
     ویکی‌پدی
    -0.68
    parsedMessage
    -0.67
    webElementXpaths
    -0.65
    POSITIVE LOGITS
     AssemblyTitle
    0.77
    <bos>
    0.77
    '
    0.57
     
    0.52
    endregion
    0.50
    [
    0.47
    垣
    0.42
    .
    0.42
    /">
    0.41
     الغ
    0.41
    Act Density 0.153%

    No Known Activations