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

    Neuronpedia

    INDEX
    Explanations

    code-related keywords like data types (string, int), XML-related words (XmlDocument, WriteTo, Element), and language keywords (var, using, return).

    oai_token-act-pair · gemini-2.0-flash

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __(/*!
    -0.73
    SuppressMessage
    -0.66
    CodeAttribute
    -0.66
    Билгалдахарш
    -0.64
    Pyx
    -0.60
     <=",
    -0.56
    webElementXpaths
    -0.56
     EconPapers
    -0.54
    RetentionPolicy
    -0.52
    Viitteet
    -0.51
    POSITIVE LOGITS
    OGND
    0.63
    Tác
    0.56
     ThemeData
    0.54
    /'+
    0.49
     Reim
    0.48
    )}</
    0.48
    ]]
    0.48
    ']],
    0.47
     ]
    0.47
    ]){
    0.47
    Act Density 0.695%

    No Known Activations