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

    Neuronpedia

    INDEX
    Explanations

    instances of the <bos> token and their context within the document

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

    Code snippets or programming-related content

    np_acts-logits-general · gemini-2.0-flash

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.66
    出版年
    -0.61
     Anſ
    -0.60
     Diſ
    -0.57
    parsedMessage
    -0.56
     AGB
    -0.55
     Houſe
    -0.55
    LookAnd
    -0.55
     Majefty
    -0.54
    XmlAccessType
    -0.52
    POSITIVE LOGITS
    complexContent
    0.51
    RectangleBorder
    0.50
    masing
    0.50
    Хьажоргаш
    0.49
     sacrific
    0.49
    颚
    0.46
    Pooling
    0.46
    的笑
    0.46
    structors
    0.46
     BorderRadius
    0.46
    Act Density 0.654%

    No Known Activations