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

    Neuronpedia

    INDEX
    Explanations

    Mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    τησε
    -0.07
     liability
    -0.07
     بندی
    -0.06
     rp
    -0.06
     commas
    -0.06
     lack
    -0.06
    530
    -0.06
     finance
    -0.06
     dummy
    -0.06
     справа
    -0.06
    POSITIVE LOGITS
    .SaveChanges
    0.07
    .What
    0.07
    .MODE
    0.07
     उनक
    0.06
    	Simple
    0.06
     해결
    0.06
    페이지
    0.06
     inspire
    0.06
     flor
    0.06
     residual
    0.06
    Act Density 0.033%

    No Known Activations