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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their emotional context in the text

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

    Emoticons using colons and parentheses

    np_acts-logits-general · gemini-2.0-flash

    emoticons and informal punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -0.73
    IntoConstraints
    -0.70
    ImageContext
    -0.66
     للمعارف
    -0.64
    Abitanti
    -0.62
     snippetHide
    -0.59
    Qual
    -0.59
    InputBorder
    -0.57
    Kontrola
    -0.56
    posób
    -0.55
    POSITIVE LOGITS
    D
    0.64
    wink
    0.57
    P
    0.55
    ::
    0.54
    nodoc
    0.53
    سكري
    0.53
    haha
    0.51
    lol
    0.51
     Haha
    0.51
    ::::
    0.50
    Act Density 0.097%

    No Known Activations