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

    Neuronpedia

    INDEX
    Explanations

    us

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     фин
    -0.07
    Fe
    -0.07
     בדי
    -0.06
     comparatively
    -0.06
    苣
    -0.06
     관심
    -0.06
    (scene
    -0.06
    畜
    -0.06
    cluded
    -0.06
    unds
    -0.06
    POSITIVE LOGITS
    _maker
    0.07
    总决赛
    0.07
    ➧
    0.07
    いますが
    0.07
    多了
    0.07
    沃尔
    0.07
    гр
    0.06
     Partial
    0.06
    博物
    0.06
    摇了摇头
    0.06
    Act Density 0.052%

    No Known Activations