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

    Neuronpedia

    INDEX
    Explanations

    mentions of mathematical conjectures and equations

    oai_token-act-pair · gemini-2.0-flash

    Con

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Con
    -2.48
    Con
    -2.39
    con
    -2.25
     con
    -2.25
     CON
    -2.03
    CON
    -1.99
     Cons
    -1.44
     cons
    -1.43
     kon
    -1.40
    Cons
    -1.38
    POSITIVE LOGITS
     myſelf
    1.15
    脚注の使い方
    1.09
    MessageTagHelper
    1.08
    تقاوى
    1.04
     cherchés
    1.03
     itſelf
    1.02
    RenderAtEndOf
    1.00
     Theſe
    0.96
     Houſe
    0.96
     ―――――
    0.95
    Act Density 8.324%

    No Known Activations