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

    Neuronpedia

    INDEX
    Explanations

    robots and AI assistants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     亠
    0.48
    igment
    0.48
    cuando
    0.46
    鿢
    0.46
     dbcontext
    0.46
     長袖
    0.45
     Enseñanza
    0.44
    攽
    0.44
     സെക്ര
    0.43
    㕝
    0.43
    POSITIVE LOGITS
     robot
    0.89
     robots
    0.83
     robotics
    0.82
    Robot
    0.79
     Robotics
    0.79
    robot
    0.74
     Robot
    0.73
     robotic
    0.72
    机器人
    0.71
     робо
    0.70
    Act Density 1.534%

    No Known Activations