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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    іли
    -0.06
     Telecom
    -0.06
     increments
    -0.06
    ери
    -0.06
     minority
    -0.06
     �
    -0.06
     abolition
    -0.06
     severed
    -0.06
     Cbd
    -0.06
     slam
    -0.06
    POSITIVE LOGITS
    (loop
    0.07
    监听页面
    0.07
     tiger
    0.06
    (topic
    0.06
     ман
    0.06
     tường
    0.06
     wikipedia
    0.06
     Ele
    0.06
    	debug
    0.06
     viêm
    0.06
    Act Density 0.000%

    No Known Activations