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

    Neuronpedia

    INDEX
    Explanations

    robots and robotics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     instruction
    0.46
     Signal
    0.45
     signal
    0.44
     Instruction
    0.44
     signaled
    0.42
     Conflict
    0.41
     SSID
    0.41
     পদ্ধতির
    0.41
     instructions
    0.40
     Token
    0.40
    POSITIVE LOGITS
     robots
    0.98
     robotics
    0.94
    机器人
    0.94
    robots
    0.90
    robot
    0.89
     robot
    0.86
    ロボ
    0.83
     робо
    0.82
     Robots
    0.82
     Robotics
    0.79
    Act Density 0.016%

    No Known Activations