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

    Neuronpedia

    INDEX
    Explanations

    │

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    global
    -0.07
    accent
    -0.07
     recovered
    -0.06
     express
    -0.06
    reb
    -0.06
     ethers
    -0.06
    ayet
    -0.06
    	pop
    -0.06
    south
    -0.06
    alles
    -0.06
    POSITIVE LOGITS
    .Index
    0.07
     Lux
    0.07
    (route
    0.07
    正在
    0.06
     │
    0.06
    │
    0.06
     lửa
    0.06
    )↵↵↵↵↵
    0.06
    .LINE
    0.06
    ORIZ
    0.06
    Act Density 0.003%

    No Known Activations