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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ican
    -0.07
     lazy
    -0.07
    нося
    -0.07
    دهای
    -0.07
    [,]
    -0.07
    foods
    -0.07
     дол
    -0.06
    /"
    -0.06
     radically
    -0.06
    idea
    -0.06
    POSITIVE LOGITS
     setState
    0.07
     prt
    0.07
     Aş
    0.06
     restraining
    0.06
    Perl
    0.06
    ूबर
    0.06
     Серед
    0.06
    ujte
    0.06
     IOError
    0.06
     Аль
    0.06
    Act Density 0.484%

    No Known Activations