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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical concepts, particularly those involving set notation or inclusions

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

    mathematical notation with specific symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.34
    கு
    -0.31
     ModelExpression
    -0.30
     comienza
    -0.30
     expériment
    -0.29
     uyar
    -0.29
     fijar
    -0.29
     doveva
    -0.28
     aguda
    -0.28
     debía
    -0.27
    POSITIVE LOGITS
    BeginContext
    0.63
     ſind
    0.61
    piram
    0.60
    principalTable
    0.60
    onViewCreated
    0.60
    InputBorder
    0.58
    featureID
    0.58
    RetentionPolicy
    0.55
     OMITBAD
    0.55
    밌
    0.55
    Act Density 0.357%

    No Known Activations