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

    Neuronpedia

    INDEX
    Explanations

    Sentence structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	tmp
    -0.07
     Carlson
    -0.06
     whales
    -0.06
    Poor
    -0.06
     captive
    -0.06
    reate
    -0.06
     foreigners
    -0.06
     swaps
    -0.06
     side
    -0.06
     끝
    -0.06
    POSITIVE LOGITS
     CGAffineTransform
    0.06
    ган
    0.06
     leo
    0.06
     موب
    0.06
     McDon
    0.06
    CUDA
    0.06
     QStringLiteral
    0.06
    Resizable
    0.06
     آور
    0.06
     ناح
    0.06
    Act Density 0.063%

    No Known Activations