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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cylinders
    -0.07
    קט
    -0.07
    riter
    -0.07
     backyard
    -0.07
     improbable
    -0.06
    (back
    -0.06
    рост
    -0.06
    퇼
    -0.06
     descr
    -0.06
     حق
    -0.06
    POSITIVE LOGITS
    血液循环
    0.07
    ꪮ
    0.06
    pair
    0.06
    .Fatalf
    0.06
     uważa
    0.06
    맬
    0.06
    ']:↵
    0.06
    存活
    0.06
    嫡
    0.06
    闫
    0.06
    Act Density 0.058%

    No Known Activations