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

    Neuronpedia

    INDEX
    Explanations

    advantage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .assertNotNull
    -0.06
    typeid
    -0.06
     Cluster
    -0.06
     Robotics
    -0.06
     Zombies
    -0.06
    CrLf
    -0.06
    (par
    -0.06
     tripod
    -0.06
    PropertyDescriptor
    -0.06
     후보
    -0.06
    POSITIVE LOGITS
     advantage
    0.08
    ESH
    0.08
    ITTLE
    0.07
     redhead
    0.07
     Để
    0.07
    Advance
    0.07
     中国
    0.07
     отмеч
    0.07
    	game
    0.06
     weapon
    0.06
    Act Density 0.020%

    No Known Activations