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

    Neuronpedia

    INDEX
    Explanations

    German castles and cities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bilden
    -0.08
     Scrum
    -0.08
     technologie
    -0.08
     conformité
    -0.08
     orthu
    -0.08
     sams
    -0.08
     pancakes
    -0.08
     Dough
    -0.07
     deklar
    -0.07
     sinc
    -0.07
    POSITIVE LOGITS
    Independent
    0.09
     shr
    0.08
     independent
    0.08
     journals
    0.08
     Влад
    0.08
    fax
    0.08
    Electronic
    0.07
    Journal
    0.07
    Coy
    0.07
    Affine
    0.07
    Act Density 0.008%

    No Known Activations