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

    Neuronpedia

    INDEX
    Explanations

    elements that indicate sections or components in a structured format, such as lists or bullet points

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

    programming syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijanski
    -0.59
    stall
    -0.55
     Keeper
    -0.54
     Beale
    -0.54
    aires
    -0.53
    glad
    -0.53
    jpa
    -0.50
    adpleegd
    -0.50
     Horde
    -0.50
    ALY
    -0.49
    POSITIVE LOGITS
    PreferredItem
    0.36
     hendes
    0.34
    CloseOperation
    0.34
    DataAnnotations
    0.31
    Personendaten
    0.30
    SourceChecksum
    0.29
     ktorí
    0.29
    GEBURTSDATUM
    0.29
    yntaxException
    0.28
     restTemplate
    0.27
    Act Density 0.069%

    No Known Activations