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

    Neuronpedia

    INDEX
    Explanations

    countries, competition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    leurs
    -0.07
    umlah
    -0.07
     geom
    -0.06
     prolific
    -0.06
    separator
    -0.06
     Yang
    -0.06
    ramento
    -0.06
    줄
    -0.06
     температура
    -0.06
    (PropertyName
    -0.06
    POSITIVE LOGITS
    ็จ
    0.07
     uncert
    0.07
     Destruction
    0.06
     we
    0.06
    Cre
    0.06
     위해
    0.06
     erm
    0.06
     destruction
    0.06
    _pago
    0.06
    ेशन
    0.06
    Act Density 0.005%

    No Known Activations