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

    Neuronpedia

    INDEX
    Explanations

    code snippets related to programming functions and their parameters

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

    Code diff indicators (@@ -[numbers]+)

    np_acts-logits-general · gemini-2.0-flash

    line numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ComponentModel
    -0.54
     [];
    -0.50
    <sup>
    -0.46
    。『
    -0.45
    *.
    -0.45
    argout
    -0.45
    %.
    -0.45
    %;
    -0.44
    外部リンク
    -0.44
     [].
    -0.43
    POSITIVE LOGITS
    TypedDataSet
    0.75
     line
    0.72
     Line
    0.72
     "..\..\..\
    0.70
     Zeile
    0.69
    脚注の使い方
    0.68
     "..\..\
    0.68
     LINE
    0.66
    Line
    0.62
    LINE
    0.61
    Act Density 0.269%

    No Known Activations