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

    Neuronpedia

    INDEX
    Explanations

    School leadership positions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     barrel
    -0.07
     mega
    -0.07
     tutorials
    -0.07
     swords
    -0.07
    麻醉
    -0.07
    _AREA
    -0.07
     bored
    -0.06
     goats
    -0.06
     ]↵↵↵
    -0.06
     bamboo
    -0.06
    POSITIVE LOGITS
    光环
    0.08
     =================================================
    0.07
     Circle
    0.07
     circle
    0.07
     incarn
    0.07
    CALL
    0.07
    饮用水
    0.07
     האחר
    0.07
    Sent
    0.07
    seconds
    0.07
    Act Density 0.048%

    No Known Activations