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

    Neuronpedia

    INDEX
    Explanations

    AI and robots programmed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    उचर
    0.47
    👂
    0.43
     кілько
    0.43
    ᄍ
    0.43
    牆
    0.42
    oost
    0.42
    ього
    0.41
    tails
    0.41
    odigd
    0.41
     ਜ਼
    0.41
    POSITIVE LOGITS
     robot
    1.15
     robots
    1.02
     Robot
    1.02
    机器人
    0.98
     robotic
    0.96
     humanoid
    0.96
    Robot
    0.93
     Robots
    0.93
     Robotic
    0.93
     Robotics
    0.84
    Act Density 0.822%

    No Known Activations