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

    Neuronpedia

    INDEX
    Explanations

    code-related terms, potentially including variable names, functions, or code structures, often also highlighting the term "leak".

    oai_token-act-pair · gemini-2.0-flash

    );

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kranz
    -0.47
    $_['
    -0.46
    Traducción
    -0.46
     passing
    -0.45
    GUN
    -0.45
    SWEET
    -0.45
    #
    -0.45
     passed
    -0.45
     FetchType
    -0.44
     Luft
    -0.44
    POSITIVE LOGITS
     EnglishChoose
    0.69
     محفوظة
    0.67
    ArgsConstructor
    0.62
     Cæsar
    0.59
    IBar
    0.58
    titleMargin
    0.57
    WebVitals
    0.57
     initComponents
    0.56
     Inhabitants
    0.55
     Beide
    0.55
    Act Density 1.610%

    No Known Activations