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

    Neuronpedia

    INDEX
    Explanations

    chapter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ikhail
    -0.08
    Luxury
    -0.08
     Convertible
    -0.08
     [&
    -0.07
    Convertible
    -0.07
     abrasive
    -0.07
    ställ
    -0.07
     stroll
    -0.07
     [](
    -0.07
     convertible
    -0.07
    POSITIVE LOGITS
    地区
    0.12
     regional
    0.12
     régional
    0.12
     local
    0.11
    Regional
    0.11
     المحلية
    0.11
    regional
    0.11
     регионе
    0.11
     localidades
    0.10
     지역
    0.10
    Act Density 0.173%

    No Known Activations