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

    Neuronpedia

    INDEX
    Explanations

    references to generated or auto-generated content

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

    code, technical terms, and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.48
     mxArray
    -0.48
     <>",
    -0.47
     ModelExpression
    -0.47
    yarnpkg
    -0.45
    aarrggbb
    -0.44
    ěry
    -0.43
    蚪
    -0.43
    contentLoaded
    -0.43
     Photocase
    -0.42
    POSITIVE LOGITS
    CodeAttribute
    0.80
    GeneratedCode
    0.56
     CURIAM
    0.54
     autorytatywna
    0.48
    jarse
    0.44
     ples
    0.41
     HEAT
    0.40
     $_[
    0.40
     ctor
    0.39
     inflex
    0.39
    Act Density 0.001%

    No Known Activations