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

    Neuronpedia

    INDEX
    Explanations

    quotations parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     основном
    -0.07
    Sphere
    -0.07
    оды
    -0.06
    isco
    -0.06
    당
    -0.06
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    -0.06
    \View
    -0.06
    روب
    -0.06
     Pik
    -0.06
     puzzled
    -0.06
    POSITIVE LOGITS
     abl
    0.07
     attainment
    0.07
     københavn
    0.07
    incoming
    0.06
    (ml
    0.06
     każ
    0.06
     начина
    0.06
    encryption
    0.06
     Manit
    0.06
     enam
    0.06
    Act Density 0.028%

    No Known Activations