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

    Neuronpedia

    INDEX
    Explanations

    heating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     asteroids
    -0.07
    跨界
    -0.07
     MU
    -0.07
    穿越
    -0.07
    棕色
    -0.07
    Florida
    -0.07
    城镇
    -0.07
     exploring
    -0.07
     Tucson
    -0.07
    """,↵
    -0.07
    POSITIVE LOGITS
     heats
    0.07
    aug
    0.07
     加
    0.07
     WithEvents
    0.07
    можем
    0.07
     kafka
    0.07
     kad
    0.07
    -update
    0.07
    栗
    0.07
    ga
    0.06
    Act Density 0.011%

    No Known Activations