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

    Neuronpedia

    INDEX
    Explanations

    numbers two and three

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    face
    -0.07
     shuttle
    -0.07
    략
    -0.07
    pei
    -0.06
    acists
    -0.06
     Vegas
    -0.06
    butt
    -0.06
    -inspired
    -0.06
    chemist
    -0.06
     reinforced
    -0.06
    POSITIVE LOGITS
    .writeInt
    0.06
    orders
    0.06
    _IList
    0.06
    	ASSERT
    0.06
    _trans
    0.06
     дити
    0.06
    (WebDriver
    0.06
     Fresh
    0.06
    。',↵
    0.06
     enticing
    0.06
    Act Density 0.006%

    No Known Activations