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

    Neuronpedia

    INDEX
    Explanations

    cumulative reward in robotics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     кредит
    0.79
     Marketing
    0.72
    clesiastical
    0.72
     роман
    0.71
    隽
    0.71
     Genealogical
    0.71
     defamation
    0.71
    Marketing
    0.71
     Jewish
    0.70
     Jews
    0.70
    POSITIVE LOGITS
     robotics
    2.15
     robot
    2.14
     robots
    2.02
     robotic
    1.93
     sensors
    1.92
     Robotics
    1.92
     Robot
    1.90
     sensor
    1.87
    Robot
    1.86
    robot
    1.81
    Act Density 0.563%

    No Known Activations