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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     망
    -0.07
    еру
    -0.06
     cada
    -0.06
    091
    -0.06
    !")
    -0.06
    /km
    -0.06
    事件
    -0.06
    व
    -0.06
    жения
    -0.06
     */
↵
↵
↵
    -0.06
    POSITIVE LOGITS
    olt
    0.07
     Exercises
    0.07
     pytest
    0.06
     stigma
    0.06
     Pry
    0.06
     chloride
    0.06
     interpolation
    0.06
     Scientists
    0.06
     Nationwide
    0.06
     infr
    0.06
    Act Density 0.002%

    No Known Activations