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

    Neuronpedia

    INDEX
    Explanations

    patterns involving the statistical distribution of data

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

    percentages and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stateProvider
    -0.47
     nakalista
    -0.46
    kháu
    -0.44
    ReactDOM
    -0.44
    Citiți
    -0.43
    ">//
    -0.40
    ----</
    -0.39
     JADX
    -0.38
    XmlAccessorType
    -0.38
    Numerade
    -0.38
    POSITIVE LOGITS
    Personensuche
    0.56
     désolés
    0.50
    mocks
    0.47
    isbol
    0.46
    ArrowToggle
    0.45
    inspace
    0.45
     Smile
    0.45
    Smile
    0.44
    évaluateur
    0.44
    óta
    0.42
    Act Density 0.083%

    No Known Activations