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

    Neuronpedia

    INDEX
    Explanations

    references and citations related to archived web content

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

    archived links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addCriterion
    -0.67
     autorytatywna
    -0.62
    ritsar
    -0.57
    arrings
    -0.57
     ब्रेकडाउन
    -0.54
     otomatig
    -0.54
    Vidite
    -0.53
    ergies
    -0.53
     Administrativna
    -0.52
     виправивши
    -0.52
    POSITIVE LOGITS
    原始内容存档于
    0.88
    Архівовано
    0.79
     оригіналу
    0.74
     arşivlendi
    0.71
     محفوظة
    0.70
    istoitu
    0.68
     копия
    0.58
    archiviato
    0.57
     مؤرشف
    0.56
     Архивировано
    0.55
    Act Density 0.023%

    No Known Activations