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

    Neuronpedia

    INDEX
    Explanations

    population numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chips
    -0.08
     recycl
    -0.08
     diamonds
    -0.08
     gummies
    -0.08
    peng
    -0.08
     DJI
    -0.08
     blazer
    -0.08
     etik
    -0.08
     trump
    -0.07
     бе
    -0.07
    POSITIVE LOGITS
     Medieval
    0.12
     medieval
    0.11
     damals
    0.10
     Census
    0.10
     wealthy
    0.10
     damal
    0.09
     famine
    0.09
     historian
    0.09
     Britannica
    0.09
     당시
    0.09
    Act Density 0.019%

    No Known Activations