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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols related to functions and their properties

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

    mathematical notation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.80
    SharedCtor
    -0.77
     ModelExpression
    -0.77
    IsMutable
    -0.76
     HasFactory
    -0.74
    GOTREF
    -0.73
    UnusedPrivate
    -0.73
     للمعارف
    -0.73
     pinulongan
    -0.73
    ItemBackground
    -0.73
    POSITIVE LOGITS
     is
    0.43
     rigtig
    0.37
     was
    0.34
     Tapia
    0.34
     nødven
    0.34
     bedeuten
    0.34
     Buch
    0.32
     sær
    0.32
     hvid
    0.32
     usually
    0.32
    Act Density 0.975%

    No Known Activations