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

    Neuronpedia

    INDEX
    Explanations

    perme

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    คณะกรรม
    -0.07
    可想
    -0.07
    IMAL
    -0.06
    꿘
    -0.06
     DAL
    -0.06
    HER
    -0.06
     Wasser
    -0.06
    还挺
    -0.06
    	LL
    -0.06
     Fair
    -0.06
    POSITIVE LOGITS
     gates
    0.07
     freezes
    0.07
    (',')
    0.07
    盯着
    0.06
     técnica
    0.06
    document
    0.06
     obra
    0.06
     Unidos
    0.06
    ,"↵
    0.06
    冊
    0.06
    Act Density 0.017%

    No Known Activations