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

    Neuronpedia

    INDEX
    Explanations

    identifiers and variable names used in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ending in "ed", often related to Java or C++ code

    np_acts-logits-general · gemini-2.0-flash

    code variable names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bkz
    -0.51
    )++;
    -0.49
    AutoScaleMode
    -0.48
    RunAsync
    -0.48
    plit
    -0.48
    Complex
    -0.47
    jara
    -0.47
    PDOException
    -0.47
     Complex
    -0.47
    ToolStrip
    -0.46
    POSITIVE LOGITS
    IntoConstraints
    0.81
    ArgsConstructor
    0.70
     nargin
    0.69
    archiviato
    0.63
    interopRequire
    0.63
    dataclass
    0.62
    HostException
    0.61
    InputBorder
    0.60
    Tracce
    0.59
    yntaxException
    0.59
    Act Density 0.071%

    No Known Activations