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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ucle
    -0.07
    Regression
    -0.07
    ΟΥΣ
    -0.06
     Canary
    -0.06
    ibu
    -0.06
    723
    -0.06
    722
    -0.06
    �
    -0.06
    Clientes
    -0.06
    017
    -0.06
    POSITIVE LOGITS
    Leader
    0.06
    >.↵
    0.06
     характер
    0.06
    ("-",
    0.06
     Gly
    0.06
     '-')↵
    0.06
     trad
    0.06
     /**↵
    0.06
     Except
    0.06
    	image
    0.06
    Act Density 0.008%

    No Known Activations