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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating expressions of opinion or controversy

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

    news and issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.48
    んびり
    -0.41
     propOrder
    -0.41
    tagHelper
    -0.40
     Seeder
    -0.36
    rungsseite
    -0.35
     knex
    -0.35
     Gig
    -0.35
    WebServlet
    -0.34
     Magnitude
    -0.34
    POSITIVE LOGITS
     autorytatywna
    0.50
    alyptus
    0.48
     EconPapers
    0.47
    utilisons
    0.43
     Gonçalves
    0.42
    Tikang
    0.41
     Hivatalos
    0.41
     öffnungszeiten
    0.40
    orszá
    0.40
    tonode
    0.40
    Act Density 0.227%

    No Known Activations