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

    Neuronpedia

    INDEX
    Explanations

    differences and comparisons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     motivate
    -0.08
    .assertIsInstance
    -0.07
    appName
    -0.07
    Nice
    -0.07
    ManagedObject
    -0.07
    bucks
    -0.07
     środk
    -0.07
     ultrasound
    -0.07
    联系我们
    -0.07
    "You
    -0.06
    POSITIVE LOGITS
     labyrinth
    0.07
    ◐
    0.07
     Tak
    0.07
     Nhật
    0.07
    製作
    0.06
    ˛
    0.06
    Ṣ
    0.06
    Прав
    0.06
    		↵↵
    0.06
    分割
    0.06
    Act Density 0.084%

    No Known Activations