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

    Neuronpedia

    INDEX
    Explanations

    code structure elements and syntax in programming language snippets

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

    Code snippets containing "var"

    np_acts-logits-general · gemini-2.0-flash

    variable declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <h1>
    -0.46
     (
    -0.44
    @
    -0.44
     besos
    -0.44
    ↵↵
    -0.44
     rodillas
    -0.43
    ↵
    -0.43
      
    -0.42
     rayas
    -0.41
     
    -0.41
    POSITIVE LOGITS
     ModelExpression
    1.35
     kasarigan
    1.34
    SequentialGroup
    1.29
     autorytatywna
    1.24
    ValueStyle
    1.21
    SourceChecksum
    1.20
    GEBURTSDATUM
    1.16
    ⤹
    1.13
     للاسماء
    1.13
    ftagPool
    1.11
    Act Density 0.429%

    No Known Activations