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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ListNode
    -0.08
    حكيم
    -0.07
    /items
    -0.07
    	cache
    -0.07
    龄
    -0.07
    干什么
    -0.07
     doping
    -0.07
    减肥
    -0.06
     overlooking
    -0.06
    Acknowled
    -0.06
    POSITIVE LOGITS
     (
    0.07
    Wall
    0.07
    购置
    0.07
     Arbitrary
    0.07
    'y
    0.06
    읶
    0.06
    ריד
    0.06
     çocuğu
    0.06
    ᑐ
    0.06
    *y
    0.06
    Act Density 0.302%

    No Known Activations