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

    Neuronpedia

    INDEX
    Explanations

    dark matter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "${
    -0.07
    ادر
    -0.07
    leurs
    -0.06
    .only
    -0.06
     мав
    -0.06
    층
    -0.06
    	String
    -0.06
    some
    -0.06
    uppet
    -0.06
    偷
    -0.06
    POSITIVE LOGITS
    toast
    0.06
     ژوئ
    0.06
     herald
    0.06
     Listing
    0.06
     programm
    0.06
     Contest
    0.06
     lime
    0.06
    Oct
    0.06
     karşılaş
    0.06
     /*----------------------------------------------------------------
    0.06
    Act Density 0.011%

    No Known Activations