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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and attributes

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

    HTML structure elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.88
    SourceChecksum
    -0.87
    CloseOperation
    -0.86
    parsedMessage
    -0.85
    ьаж
    -0.82
    Искәрмәләр
    -0.81
    featureID
    -0.81
     Roskov
    -0.80
    StructEnd
    -0.80
     MainAxisSize
    -0.79
    POSITIVE LOGITS
     names
    0.38
     list
    0.38
     Dem
    0.32
     
    0.31
     B
    0.31
     Fenster
    0.31
     Memory
    0.30
     b
    0.30
     esempi
    0.30
     sum
    0.30
    Act Density 0.017%

    No Known Activations