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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nintendo
    -0.07
    ่อ
    -0.06
    	Delete
    -0.06
     Piano
    -0.06
     amino
    -0.06
     नए
    -0.06
     Hive
    -0.06
    Π
    -0.06
     Upgrade
    -0.06
     ETA
    -0.06
    POSITIVE LOGITS
     class
    0.09
     jeans
    0.08
    -class
    0.07
    class
    0.07
    CLASS
    0.07
     traditional
    0.06
     چاپ
    0.06
     clearColor
    0.06
    ,class
    0.06
    llum
    0.06
    Act Density 0.008%

    No Known Activations