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

    Neuronpedia

    INDEX
    Explanations

    Harry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KeyListener
    -0.07
     sunglasses
    -0.06
    ception
    -0.06
    ارش
    -0.06
    contained
    -0.06
    Ad
    -0.06
    Transformation
    -0.06
    CardBody
    -0.06
     hä
    -0.06
    III
    -0.06
    POSITIVE LOGITS
    .previous
    0.07
    (clazz
    0.07
    DockControl
    0.06
     durable
    0.06
    ・━
    0.06
     갤로그로
    0.06
     fit
    0.06
     програм
    0.06
     letz
    0.06
    trajectory
    0.06
    Act Density 0.013%

    No Known Activations