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

    Neuronpedia

    INDEX
    Explanations

    fonts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     לק
    -0.07
    蝌
    -0.07
    带动
    -0.07
    ល
    -0.06
     każdy
    -0.06
    各种
    -0.06
    蘭
    -0.06
    _Array
    -0.06
     Gon
    -0.06
    禁
    -0.06
    POSITIVE LOGITS
     modelAndView
    0.08
     throne
    0.07
     YEARS
    0.07
     어렵
    0.07
    DisplayStyle
    0.07
    (always
    0.07
    (event
    0.07
    	size
    0.07
    Great
    0.07
    [OF
    0.07
    Act Density 0.010%

    No Known Activations