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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    perial
    -0.08
    .a
    -0.08
    باشد
    -0.07
    mobile
    -0.07
    ブ
    -0.07
     Imperial
    -0.07
    ambre
    -0.07
     참고
    -0.07
     Apartment
    -0.06
     نيز
    -0.06
    POSITIVE LOGITS
    (Customer
    0.07
    duplicate
    0.07
     söy
    0.06
     dang
    0.06
    .getDay
    0.06
    ]init
    0.06
     Tillerson
    0.06
    Distinct
    0.05
    ytic
    0.05
     banners
    0.05
    Act Density 0.041%

    No Known Activations