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

    Neuronpedia

    INDEX
    Explanations

    the formatting of bullet points or lists in written content

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

    emoticons or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gestone
    -0.75
     تضيفلها
    -0.73
     Eilish
    -0.72
     arşivlendi
    -0.69
    cticut
    -0.69
    httphttps
    -0.68
     increí
    -0.66
    majánló
    -0.66
    存于互联网档案馆
    -0.66
     Grüsse
    -0.65
    POSITIVE LOGITS
    :-
    0.91
    {-
    0.79
     :-
    0.77
    ;-
    0.75
    .-
    0.75
     (-
    0.75
    =-
    0.74
     -
    0.72
    !-
    0.72
    ,-
    0.71
    Act Density 0.043%

    No Known Activations