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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     copy
    -0.08
     funktion
    -0.08
    -0.08
     copied
    -0.08
     fonction
    -0.07
    ایت
    -0.07
     BIO
    -0.07
     orient
    -0.07
    _function
    -0.07
    POR
    -0.07
    POSITIVE LOGITS
    Sum
    0.09
     сумма
    0.09
     ಸುಮ
    0.09
     Sum
    0.09
    ौती
    0.08
    .Sum
    0.08
     melodic
    0.08
     والمؤ
    0.08
     求
    0.08
     mør
    0.08
    Act Density 0.020%
    No Known Activations