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

    Neuronpedia

    INDEX
    Explanations

    the use of introductory phrases that set the context for explanations or discussions in a document

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

    "In" followed by a determiner or noun

    np_acts-logits-general · gemini-2.0-flash

    in phrases like "in contrast" or "in this case"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    抱
    -0.39
     demostrado
    -0.39
    君
    -0.38
     提示
    -0.38
     recev
    -0.38
     cappello
    -0.37
     consejos
    -0.36
    종
    -0.35
    WebServlet
    -0.35
    datetime
    -0.35
    POSITIVE LOGITS
     صوتيه
    0.94
     referenties
    0.84
     Drapeau
    0.80
    SharedCtor
    0.76
    Portail
    0.76
     Wiktionnaire
    0.73
     Wallflower
    0.71
    بوابة
    0.70
     المعيارى
    0.68
     ProtoMessage
    0.66
    Act Density 0.720%

    No Known Activations