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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Census
    -0.07
     특정
    -0.07
     Turk
    -0.07
    けれど
    -0.07
     Roe
    -0.07
     Ernst
    -0.07
     побед
    -0.07
     görün
    -0.06
     country
    -0.06
    haus
    -0.06
    POSITIVE LOGITS
    _day
    0.07
    mixed
    0.07
    AILS
    0.07
    ladığı
    0.07
     enjoying
    0.07
    .booking
    0.07
     optimum
    0.07
    (py
    0.07
     recommended
    0.07
    advanced
    0.07
    Act Density 0.019%

    No Known Activations