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

    Neuronpedia

    INDEX
    Explanations

    occurrences of whitespace or line breaks in the document

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

    foreign words and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.73
    RectangleBorder
    -0.62
    ftagPool
    -0.60
    RenderAtEndOf
    -0.60
     تضيفلها
    -0.57
     ProtoMessage
    -0.55
    InputBorder
    -0.55
    ArgsConstructor
    -0.54
     unknownFields
    -0.53
    kloped
    -0.52
    POSITIVE LOGITS
    
    0.47
     disambiguazione
    0.41
    Dabei
    0.38
    Plant
    0.38
     avoient
    0.37
     للاسماء
    0.37
    ſelves
    0.37
    Tur
    0.36
    󠁧
    0.36
     Sơn
    0.35
    Act Density 0.001%

    No Known Activations