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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﺩ
    -0.07
    ⍣
    -0.07
    深度
    -0.07
    赳
    -0.07
    ӡ
    -0.07
    卤
    -0.07
     ebook
    -0.06
     Afghanistan
    -0.06
    .HttpSession
    -0.06
    _intr
    -0.06
    POSITIVE LOGITS
     сфере
    0.07
    "W
    0.07
    	menu
    0.07
    heits
    0.07
    _company
    0.07
     '='
    0.07
     ("
    0.06
    nable
    0.06
    Patch
    0.06
    在这个
    0.06
    Act Density 0.001%

    No Known Activations