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

    Neuronpedia

    INDEX
    Explanations

    the general theme of literary reviews

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

    authors or books

    np_acts-logits-general · gemini-2.0-flash

    author names listed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.61
    Życiorys
    -0.59
    URLException
    -0.56
     légende
    -0.52
    IsContent
    -0.51
    cinoma
    -0.51
    SharedDtor
    -0.51
    SequentialGroup
    -0.50
     rospy
    -0.49
     ditemp
    -0.48
    POSITIVE LOGITS
     author
    0.67
     Goodreads
    0.62
     Author
    0.60
     autorytatywna
    0.59
     authors
    0.59
     bestselling
    0.58
    Author
    0.58
     books
    0.57
    Goodreads
    0.57
     lenker
    0.57
    Act Density 0.165%

    No Known Activations