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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    短期
    -0.09
     szczegół
    -0.09
    鹈
    -0.07
    vidence
    -0.07
     obt
    -0.07
     образования
    -0.07
    دليل
    -0.07
    累积
    -0.07
    幺
    -0.07
    东京
    -0.07
    POSITIVE LOGITS
    mps
    0.07
    𝐀
    0.07
    \Module
    0.07
    	a
    0.07
    leg
    0.07
    izer
    0.07
    printer
    0.07
    (inputs
    0.06
     [];
↵
    0.06
    ;a
    0.06
    Act Density 0.001%

    No Known Activations