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

    Neuronpedia

    INDEX
    Explanations

    math sets (x, y)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Garrett
    -0.09
     Trey
    -0.09
     latina
    -0.08
    CMP
    -0.08
     Chevy
    -0.08
    Copper
    -0.08
     Fender
    -0.08
     Tiffany
    -0.08
     Freddie
    -0.08
     Weiss
    -0.07
    POSITIVE LOGITS
     ironically
    0.09
    側
    0.08
     technically
    0.07
    represented
    0.07
     बाज
    0.07
    /e
    0.07
     comparatively
    0.07
     contempt
    0.07
     jüng
    0.07
     reson
    0.07
    Act Density 0.292%

    No Known Activations