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

    Neuronpedia

    INDEX
    Explanations

    Law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dt
    -0.07
     도시
    -0.07
     rolling
    -0.06
     amplifier
    -0.06
    startDate
    -0.06
     mirror
    -0.06
     ]]
    -0.06
    ерп
    -0.06
     является
    -0.06
     програм
    -0.06
    POSITIVE LOGITS
    ="{{
    0.07
     Amit
    0.06
     Ren
    0.06
     záb
    0.06
    用的
    0.06
    .auth
    0.06
    وال
    0.06
    641
    0.06
    明
    0.06
     consolation
    0.06
    Act Density 0.078%

    No Known Activations