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

    Neuronpedia

    INDEX
    Explanations

    game theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    参数
    -0.09
     парамет
    -0.08
     parameter
    -0.08
     chatbot
    -0.08
     SDK
    -0.08
     messen
    -0.08
    PARAM
    -0.07
     figsize
    -0.07
    为什么
    -0.07
     Savage
    -0.07
    POSITIVE LOGITS
     redistribution
    0.14
     Redistribution
    0.14
     redistribute
    0.13
     distributing
    0.13
     redistributed
    0.12
    distribution
    0.11
    Distrib
    0.10
     निध
    0.10
     donating
    0.10
    Distribution
    0.10
    Act Density 0.011%

    No Known Activations