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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that separate clauses or items in a list

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

    lists of names or initials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.49
    /
    -0.49
    ,
    -0.47
    offsetof
    -0.47
    XmlAccessType
    -0.45
    ांकि
    -0.40
     indefinitely
    -0.39
     الكه
    -0.39
     single
    -0.39
    ierno
    -0.39
    POSITIVE LOGITS
     którzy
    0.61
    themselves
    0.61
     Theſe
    0.60
     eds
    0.56
     kteří
    0.54
     المعيارى
    0.54
     CURIAM
    0.54
    يكب
    0.52
     Jr
    0.52
    出版年
    0.52
    Act Density 0.113%

    No Known Activations