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

    Neuronpedia

    INDEX
    Explanations

    Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خاصة
    -0.07
    rine
    -0.07
     verifica
    -0.07
     zij
    -0.07
     realtà
    -0.07
     certainly
    -0.07
     inevitable
    -0.07
    ência
    -0.07
     fever
    -0.07
    比较
    -0.06
    POSITIVE LOGITS
    RoutingModule
    0.08
    镶
    0.08
     STATIC
    0.08
     stripslashes
    0.07
    browse
    0.07
     carpets
    0.07
    ฉาก
    0.07
    ◁
    0.07
    ossil
    0.07
    LOOP
    0.07
    Act Density 0.041%

    No Known Activations