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

    Neuronpedia

    INDEX
    Explanations

    parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Auto
    -0.07
     Sex
    -0.07
    roduced
    -0.06
    United
    -0.06
     Singh
    -0.06
    Facade
    -0.06
     VStack
    -0.06
     symmetric
    -0.06
    یف
    -0.06
    ?"↵↵
    -0.06
    POSITIVE LOGITS
    acker
    0.07
    ประม
    0.07
    logged
    0.06
    ดย
    0.06
    	Player
    0.06
    �
    0.06
    ‐‐
    0.06
    isinin
    0.06
    盛
    0.06
     bows
    0.06
    Act Density 0.007%

    No Known Activations