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

    Neuronpedia

    INDEX
    Explanations

    immigration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Double
    -0.08
     Double
    -0.08
     گردد
    -0.08
    dbl
    -0.08
     Underground
    -0.08
     Sorgen
    -0.08
    	double
    -0.08
     кафед
    -0.08
     Starts
    -0.08
     Debit
    -0.08
    POSITIVE LOGITS
     Liu
    0.09
     пух
    0.08
     guns
    0.08
     luck
    0.08
     оцен
    0.08
     оценки
    0.07
     avaliação
    0.07
     двиг
    0.07
    评
    0.07
     gale
    0.07
    Act Density 0.004%

    No Known Activations