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

    Neuronpedia

    INDEX
    Explanations

    specific titles or quotes of books and publications

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

    Text within quotation marks, often titles

    np_acts-logits-general · gemini-2.0-flash

    introduces titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.70
    出版年
    -0.53
     typelib
    -0.51
     فريبيس
    -0.51
     cuillère
    -0.51
     rowspan
    -0.50
    phinx
    -0.50
     Gossip
    -0.50
     REFER
    -0.50
     GBIF
    -0.50
    POSITIVE LOGITS
     The
    0.68
     titulada
    0.60
     entitled
    0.56
    SequentialGroup
    0.56
    cektir
    0.56
    unate
    0.54
    見えて
    0.53
    ISupport
    0.53
    ままで
    0.52
     berjudul
    0.52
    Act Density 0.124%

    No Known Activations