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

    Neuronpedia

    INDEX
    Explanations

    occurrences of statistical analysis results and measurements

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

    Code, programming, and software snippets

    np_acts-logits-general · gemini-2.0-flash

    documentation, code, HTML tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.60
    )、
    -0.58
    cookieParser
    -0.52
    verwijspagina
    -0.52
    ENSIS
    -0.52
    oredCriteria
    -0.50
     bpy
    -0.49
    chọn
    -0.49
    saraba
    -0.49
    %);
    -0.48
    POSITIVE LOGITS
    <eos>
    1.51
    </tbody>
    0.86
    ↵↵
    0.83
    ↵↵↵↵
    0.80
    ↵↵↵↵↵
    0.79
    <h3>
    0.76
    <h2>
    0.75
    <h4>
    0.75
     Disclaimer
    0.74
    ↵↵↵↵↵↵↵
    0.73
    Act Density 1.197%

    No Known Activations