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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters associated with dialogue or quotations

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

    's contraction suffixes or followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikimedijinoj
    -0.71
    rrggbb
    -0.59
     seat
    -0.58
     ويكيميديا
    -0.56
     {};
    -0.52
     "..\..\
    -0.52
     "'");
    -0.51
    )))));
    -0.50
    adpleegd
    -0.50
    seat
    -0.49
    POSITIVE LOGITS
    tagHelperRunner
    0.66
    tahui
    0.63
    Viited
    0.60
    lorette
    0.58
    帖最后由
    0.56
     onResponse
    0.56
     defaultstate
    0.54
    Revenir
    0.53
    TagMode
    0.51
    gimento
    0.51
    Act Density 0.001%

    No Known Activations