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

    Neuronpedia

    INDEX
    Explanations

    elements related to structured data formats or code snippets

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

    key-value pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.62
    IsMutable
    -0.61
     betweenstory
    -0.59
    thâu
    -0.58
    httphttps
    -0.53
     للمعارف
    -0.52
    tangentMode
    -0.51
    DoubleQuotes
    -0.50
    PropertyChanging
    -0.50
    :✨
    -0.48
    POSITIVE LOGITS
     answer
    0.40
     Answers
    0.39
    Personendaten
    0.39
    quelize
    0.38
     answers
    0.38
    PostExecute
    0.36
    thenReturn
    0.34
     χ
    0.33
     implementation
    0.33
    ynthetic
    0.33
    Act Density 0.161%

    No Known Activations