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

    Neuronpedia

    INDEX
    Explanations

    references to legal claims and court-related terminology

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

    alleges claims attaches seeks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     everywhere
    -0.38
     Paglinawan
    -0.36
     expert
    -0.34
    Admin
    -0.33
     объя
    -0.33
     Zug
    -0.33
    Ver
    -0.33
     continúas
    -0.32
     aver
    -0.32
    Sum
    -0.32
    POSITIVE LOGITS
     GenerationType
    0.56
    0.55
    arashtra
    0.55
    niſſe
    0.54
     Geſch
    0.53
     queſta
    0.53
    lysm
    0.53
    spodnie
    0.52
    MessageTagHelper
    0.52
    出版年
    0.52
    Act Density 0.772%

    No Known Activations