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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Giấy
    -0.08
    ">-->↵
    -0.07
     McM
    -0.07
    .DriverManager
    -0.07
     Marc
    -0.07
    母亲
    -0.06
     stall
    -0.06
    �
    -0.06
     suo
    -0.06
    ROT
    -0.06
    POSITIVE LOGITS
     yapılan
    0.07
    人民共和国
    0.06
    ERICAN
    0.06
     imperialism
    0.06
    维
    0.06
    [](
    0.06
     stats
    0.06
    	m
    0.06
     Fridays
    0.06
     filtering
    0.06
    Act Density 0.000%

    No Known Activations