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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    because
    -0.06
     Fletcher
    -0.06
     Sutton
    -0.06
    million
    -0.06
    Robot
    -0.06
     aún
    -0.06
    .InteropServices
    -0.06
     suing
    -0.06
    Introduction
    -0.06
    虽然
    -0.06
    POSITIVE LOGITS
     xin
    0.07
     foundations
    0.07
    asing
    0.07
    	super
    0.07
    Config
    0.06
     '">'
    0.06
    .')↵
    0.06
     Invoke
    0.06
    ộp
    0.06
     fragrance
    0.06
    Act Density 0.038%

    No Known Activations