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

    Neuronpedia

    INDEX
    Explanations

    movies, plays, television

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    主任
    -0.06
     обо
    -0.05
     alma
    -0.05
     T
    -0.05
     입
    -0.05
    .notifications
    -0.05
     Conte
    -0.05
    actal
    -0.05
    (App
    -0.05
    .z
    -0.05
    POSITIVE LOGITS
     *)[
    0.08
    ikipedia
    0.07
    uy�
    0.07
     黄
    0.07
    @RunWith
    0.06
     equations
    0.06
     Replacement
    0.06
     sơn
    0.06
     Bylo
    0.06
    REATE
    0.06
    Act Density 0.065%

    No Known Activations