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

    Neuronpedia

    INDEX
    Explanations

    33.33

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pewno
    -0.09
     unbedingt
    -0.08
    ，以及
    -0.08
    πε
    -0.08
     chł
    -0.08
     takut
    -0.07
    Helmet
    -0.07
     ota
    -0.07
     Stamp
    -0.07
    Working
    -0.07
    POSITIVE LOGITS
     universal
    0.09
     కార
    0.08
     enforce
    0.08
     सार्व
    0.07
     chem
    0.07
     universally
    0.07
     arra
    0.07
     view
    0.07
     dissolved
    0.07
     કાર
    0.07
    Act Density 0.016%

    No Known Activations