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

    Neuronpedia

    INDEX
    Explanations

    words signifying emphasis, quantity, or legal jargon.

    oai_token-act-pair · gemini-2.0-flash

    disclaimers and conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vie
    -0.49
     Out
    -0.47
     (
    -0.46
     provided
    -0.43
     alternative
    -0.42
     B
    -0.42
    "\"
    -0.41
    Kanpo
    -0.41
    ร์
    -0.41
     "
    -0.41
    POSITIVE LOGITS
     EconPapers
    1.23
     ModelExpression
    0.96
    AndEndTag
    0.94
    DoubleQuotes
    0.94
     الاطلاع
    0.94
    ########.
    0.94
    OGND
    0.91
    MessageOf
    0.90
     Audiodateien
    0.89
    TypedDataSet
    0.85
    Act Density 2.113%

    No Known Activations