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

    Neuronpedia

    INDEX
    Explanations

    closing punctuation marks and parentheses in code snippets

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

    programming code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.52
    domada
    -0.49
     Taktlose
    -0.48
    ंदीखरीदारी
    -0.48
    uxxxx
    -0.48
    +#+#
    -0.48
     betweenstory
    -0.47
    GTCX
    -0.45
    ategy
    -0.44
    渉
    -0.43
    POSITIVE LOGITS
     greateſt
    0.49
    apnews
    0.47
     चीज़ों
    0.47
     fubject
    0.46
     viewDidLoad
    0.43
     Menschheit
    0.41
     nôtre
    0.40
    GRANTED
    0.40
     invloed
    0.40
     oorspron
    0.39
    Act Density 0.027%

    No Known Activations