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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .assertEqual
    -0.07
    塔
    -0.06
    .UI
    -0.06
     başladı
    -0.06
     lien
    -0.06
     conductor
    -0.06
     здоров
    -0.06
     resembling
    -0.06
    .Toast
    -0.06
     believers
    -0.06
    POSITIVE LOGITS
    getAttribute
    0.07
     صنعت
    0.07
     CrossRef
    0.06
     Watkins
    0.06
    污
    0.06
     olanlar
    0.06
     ]
    0.06
     Ratings
    0.06
     otáz
    0.06
     Census
    0.06
    Act Density 0.018%

    No Known Activations