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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    橙
    -0.08
     carnival
    -0.08
     Tonight
    -0.07
    棕
    -0.07
     Crimson
    -0.07
     planets
    -0.07
     Judge
    -0.06
    صنع
    -0.06
    医科大学
    -0.06
    演绎
    -0.06
    POSITIVE LOGITS
    emen
    0.07
    _GATE
    0.07
    BackPressed
    0.07
     complying
    0.06
    льц
    0.06
    一般人
    0.06
    国资委
    0.06
    ÜR
    0.06
    实事求
    0.06
    speaker
    0.06
    Act Density 0.000%

    No Known Activations