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

    Neuronpedia

    INDEX
    Explanations

    formatting characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /template
    -0.07
    碧桂园
    -0.07
    uren
    -0.07
    ilinx
    -0.07
    ziej
    -0.07
    熹
    -0.07
    报废
    -0.06
    tsky
    -0.06
    zsche
    -0.06
     censorship
    -0.06
    POSITIVE LOGITS
    的社会
    0.07
     Dan
    0.07
     array
    0.06
     {}).
    0.06
    	Return
    0.06
     quand
    0.06
     всяк
    0.06
    场合
    0.06
    artment
    0.06
    �
    0.06
    Act Density 0.037%

    No Known Activations