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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     number
    -0.08
    枯燥
    -0.07
    ContentPane
    -0.07
    conc
    -0.07
     selenium
    -0.06
    ตรา
    -0.06
    ﱁ
    -0.06
    Solution
    -0.06
     narrower
    -0.06
    ение
    -0.06
    POSITIVE LOGITS
    économ
    0.08
     cps
    0.07
    ossil
    0.07
    ">',
    0.07
    出入境
    0.07
     AAP
    0.07
     Aspect
    0.07
     UIB
    0.06
    深入推进
    0.06
     lässt
    0.06
    Act Density 0.078%

    No Known Activations