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

    Neuronpedia

    INDEX
    Explanations

    math/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     přest
    -0.06
    	use
    -0.06
                
    -0.06
     x
    -0.06
    定义
    -0.06
     процесса
    -0.06
    	add
    -0.06
     �
    -0.06
    ショ
    -0.06
    冬
    -0.06
    POSITIVE LOGITS
    Calendar
    0.07
    oste
    0.07
    (stypy
    0.07
    constexpr
    0.07
     Fakült
    0.06
    Without
    0.06
    دو
    0.06
    olics
    0.06
    ">#
    0.06
     بسی
    0.06
    Act Density 0.024%

    No Known Activations