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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    这话
    -0.08
     nguyên
    -0.07
     Hotel
    -0.07
    persons
    -0.07
     Recipe
    -0.07
    منهج
    -0.06
     SIDE
    -0.06
     Defendants
    -0.06
     SON
    -0.06
     toe
    -0.06
    POSITIVE LOGITS
    eroon
    0.07
    口碑
    0.07
     встреча
    0.06
     współprac
    0.06
    .getUserId
    0.06
     surround
    0.06
    Boost
    0.06
     imaginary
    0.06
     Herrera
    0.06
     Aust
    0.06
    Act Density 0.156%

    No Known Activations