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

    Neuronpedia

    INDEX
    Explanations

    code, particularly methods/functions and API requests, characterized by keywords like "public," "return," and references to objects and parameters

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .
    -0.59
    ,
    -0.56
    ↵↵
    -0.56
    <eos>
    -0.53
    ito
    -0.49
    ana
    -0.49
     nearly
    -0.49
     the
    -0.47
    ’
    -0.46
    ;
    -0.44
    POSITIVE LOGITS
     AssemblyCulture
    1.31
    RenderAtEndOf
    1.31
     تضيفلها
    1.08
    SourceChecksum
    1.01
     initComponents
    1.00
    IsContent
    0.99
    IntoConstraints
    0.98
     للمعارف
    0.97
    ThroughAttribute
    0.97
    tagHelperRunner
    0.96
    Act Density 2.223%

    No Known Activations