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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships within a text

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

    percentages and probabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     insuffisamment
    -0.54
    httphttps
    -0.53
    bcryptjs
    -0.52
     disambiguazione
    -0.50
     للاسماء
    -0.48
    didSet
    -0.47
    WebElementEntity
    -0.47
     kasarigan
    -0.46
     BoxDecoration
    -0.46
     autorytatywna
    -0.45
    POSITIVE LOGITS
    waitKey
    0.46
    marginHorizontal
    0.45
     £
    0.44
    paddingVertical
    0.43
     less
    0.43
    cifix
    0.43
    BuilderFactory
    0.42
     anteriore
    0.42
     Halen
    0.41
     softer
    0.41
    Act Density 0.106%

    No Known Activations