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

    Neuronpedia

    INDEX
    Explanations

    Python programming language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mui
    -0.08
     harvest
    -0.08
     malaria
    -0.08
     hydraulic
    -0.08
    slick
    -0.08
    _cuda
    -0.07
     keen
    -0.07
     hectares
    -0.07
     greens
    -0.07
    Thai
    -0.07
    POSITIVE LOGITS
     Satan
    0.10
     kerk
    0.09
     neurotrans
    0.09
    	Int
    0.09
     interpreter
    0.08
     Church
    0.08
     Kirche
    0.08
     اظ
    0.08
     igles
    0.08
     Leib
    0.08
    Act Density 0.014%

    No Known Activations