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

    Neuronpedia

    INDEX
    Explanations

    formatted or structured data, particularly in terms of headings and tables

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

    structured formatting and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.90
    windowFixed
    -0.86
    tagHelperRunner
    -0.85
    featureID
    -0.76
    rrggbb
    -0.76
    oredCriteria
    -0.75
    MigrationBuilder
    -0.75
    Jeografia
    -0.74
     الرياضيه
    -0.74
    StructEnd
    -0.73
    POSITIVE LOGITS
     (
    0.28
      
    0.27
     et
    0.27
     {
    0.27
     another
    0.26
     "
    0.26
     [*]
    0.26
     
    0.26
    ↵
    0.25
    ($
    0.25
    Act Density 0.393%

    No Known Activations