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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific formatting, possibly indicating a focus on structuring sentences or clauses

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

    Punctuation or symbols followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    punctuation, symbols, and diverse languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     #
    -0.50
    roy
    -0.48
     
    -0.48
     "
    -0.48
     om
    -0.47
    lug
    -0.47
     أنّ
    -0.46
     (
    -0.46
    τέ
    -0.46
    RefNanny
    -0.45
    POSITIVE LOGITS
     ​​
    1.78
    出版年
    1.01
     referenties
    0.91
     שוליים
    0.88
     HttpNotFound
    0.81
    ……"
    0.80
     ampoule
    0.78
    原始内容存档于
    0.78
     متعلقه
    0.77
    amp
    0.76
    Act Density 1.624%

    No Known Activations