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

    Neuronpedia

    INDEX
    Explanations

    George

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     akan
    -0.07
    upon
    -0.06
     Sınıf
    -0.06
     mixins
    -0.06
     холод
    -0.06
    .Inter
    -0.06
    colour
    -0.06
    (['
    -0.06
    INIT
    -0.06
    عنی
    -0.06
    POSITIVE LOGITS
     George
    0.15
    orge
    0.15
     Jorge
    0.14
    George
    0.14
    orges
    0.11
     Georges
    0.11
     gorge
    0.09
    นก
    0.07
     جور
    0.07
    	vertex
    0.06
    Act Density 0.003%

    No Known Activations