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

    Neuronpedia

    INDEX
    Explanations

    emoticons and expressions of humor or laughter

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

    Emoticons and smileys

    np_acts-logits-general · gemini-2.0-flash

    positive emoticons and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?")
    -0.70
    %");
    -0.70
    ?");
    -0.69
     □
    -0.68
    IMPORTED
    -0.67
    ˏ
    -0.65
    %";
    -0.64
    NUMX
    -0.63
    ?」
    -0.62
    errHandler
    -0.62
    POSITIVE LOGITS
    <eos>
    0.67
     Especially
    0.61
    !
    0.57
    ゞ
    0.56
     Also
    0.54
     But
    0.53
     Anyway
    0.52
     Just
    0.51
     Those
    0.50
     Although
    0.50
    Act Density 0.114%

    No Known Activations