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

    Neuronpedia

    INDEX
    Explanations

    elements related to data types and their attributes

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

    code syntax or structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.59
     հղումներ
    -0.51
    Tracce
    -0.48
     estekak
    -0.46
    ConstraintMaker
    -0.46
    kapat
    -0.45
     שוליים
    -0.45
    ViewFeatures
    -0.44
    WebServlet
    -0.42
     setContent
    -0.42
    POSITIVE LOGITS
     flag
    0.44
    oredCriteria
    0.43
    flag
    0.42
    Flag
    0.40
    ArrowToggle
    0.40
    AsUp
    0.38
    simpleType
    0.38
    Code
    0.38
    code
    0.37
     Flag
    0.35
    Act Density 0.131%

    No Known Activations