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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /***/
    -0.07
    ların
    -0.07
     pornos
    -0.07
     تأ
    -0.07
     витами
    -0.07
     corres
    -0.07
     EOS
    -0.07
    425
    -0.06
    halb
    -0.06
    ，再
    -0.06
    POSITIVE LOGITS
    (mean
    0.06
    _er
    0.06
     modulo
    0.06
    /n
    0.06
     gyr
    0.06
    .Require
    0.06
    Democrats
    0.06
     ấn
    0.06
     )(
    0.06
     '),
    0.06
    Act Density 0.002%

    No Known Activations