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

    Neuronpedia

    INDEX
    Explanations

    '

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fu
    -0.07
    ôte
    -0.06
    рій
    -0.06
    ené
    -0.06
     Ronaldo
    -0.06
     Yosh
    -0.06
    rzy
    -0.06
     KP
    -0.06
     argv
    -0.06
     Newspaper
    -0.06
    POSITIVE LOGITS
    etrofit
    0.07
     {!!
    0.07
    irst
    0.06
     lexer
    0.06
    _GROUP
    0.06
    .Async
    0.06
     проб
    0.06
    (stypy
    0.06
     смесь
    0.06
    ิตย
    0.06
    Act Density 0.003%

    No Known Activations