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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax elements or operations

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

    code ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Clas
    -0.31
    JvmStatic
    -0.31
     obie
    -0.31
     بلغ
    -0.31
    Total
    -0.29
    Tab
    -0.28
     charité
    -0.28
     pierre
    -0.28
     Verein
    -0.27
     kov
    -0.27
    POSITIVE LOGITS
    XmlType
    0.60
    0.59
     EconPapers
    0.57
    parsedMessage
    0.56
     ujednoznacz
    0.56
     AssemblyTitle
    0.55
     useAppContext
    0.53
    SequentialGroup
    0.51
     transfieras
    0.50
    utilisons
    0.50
    Act Density 0.030%

    No Known Activations