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

    Neuronpedia

    INDEX
    Explanations

    references to the contents of documents or files

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

    contents of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.50
     defaultstate
    -0.50
     purpoſe
    -0.48
    もしれません
    -0.48
    ImageContext
    -0.48
    Cyfarwyddwr
    -0.48
     JUGA
    -0.47
     $_(
    -0.47
     itſelf
    -0.47
     ſch
    -0.46
    POSITIVE LOGITS
     ContentValues
    0.56
    content
    0.48
    Contenu
    0.45
     contents
    0.44
     Inhalt
    0.44
     inhoud
    0.44
    の内容
    0.43
    ContentValues
    0.43
     内容
    0.42
    CONTENT
    0.41
    Act Density 0.035%

    No Known Activations