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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" in various grammatical constructions

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

    is followed by description or negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $_(
    -0.57
    WebServlet
    -0.56
    ftagPool
    -0.54
     Cæsar
    -0.53
    ########.
    -0.52
     Majefty
    -0.50
     désolés
    -0.50
    fjspx
    -0.48
    ResponseWriter
    -0.48
    CloseOperation
    -0.48
    POSITIVE LOGITS
    guenos
    0.45
     NSCoder
    0.40
     arşivlendi
    0.39
    îtra
    0.39
     numberOfRows
    0.36
    httphttps
    0.36
    Đây
    0.36
    LEGGI
    0.35
    imágenes
    0.34
    adaptiveStyles
    0.34
    Act Density 0.546%

    No Known Activations