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

    Neuronpedia

    INDEX
    Explanations

    assignment operations and their associated values in code

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

    Equals signs in code or data

    np_acts-logits-general · gemini-2.0-flash

    Python and C++ code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "/";
    -0.75
     [];
    -0.66
     '/';
    -0.66
     [];
    -0.66
     ";
    -0.64
    ';
    -0.63
    ()?;
    -0.62
     ".";
    -0.61
     "-";
    -0.61
    ";
    -0.59
    POSITIVE LOGITS
     AssemblyTitle
    0.69
     purpoſe
    0.68
    SBATCH
    0.67
    WindowConstants
    0.66
     المعيارى
    0.65
    WireFormatLite
    0.65
    Спољашње
    0.63
     depositphotos
    0.63
    +#+#
    0.63
    aronder
    0.62
    Act Density 0.193%

    No Known Activations