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

    Neuronpedia

    INDEX
    Explanations

    closing braces and end statements in code snippets

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

    Code block endings (e.g., "}") and keywords

    np_acts-logits-general · gemini-2.0-flash

    end of code block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otherwise
    -0.87
    Otherwise
    -0.81
     OTHERWISE
    -0.80
     other
    -0.79
    otherwise
    -0.77
     Otherwise
    -0.77
     ELSE
    -0.70
     Else
    -0.67
     الأخرى
    -0.65
     ellers
    -0.63
    POSITIVE LOGITS
    InputBorder
    0.68
    ↵
    0.58
     typelib
    0.56
    SizeF
    0.56
    //});
    0.56
    Eventually
    0.55
     وصلة
    0.55
    //</
    0.54
     finally
    0.54
    finally
    0.53
    Act Density 0.036%

    No Known Activations