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

    Neuronpedia

    INDEX
    Explanations

    to let allow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     поверхность
    -0.07
    OfWeek
    -0.06
     hin
    -0.06
     Cel
    -0.06
     док
    -0.06
    ût
    -0.06
     aracılığıyla
    -0.06
     YORK
    -0.06
    нение
    -0.06
    环
    -0.06
    POSITIVE LOGITS
    _VALUES
    0.07
    .Company
    0.07
     vriend
    0.07
     Walk
    0.07
    redict
    0.07
    客
    0.06
     Matlab
    0.06
     Ferm
    0.06
     Democr
    0.06
     Explicit
    0.06
    Act Density 0.015%

    No Known Activations