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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [@
    -0.08
    -pe
    -0.07
    庆祝
    -0.07
    aps
    -0.07
    砰
    -0.07
     AUTHORS
    -0.07
    Aff
    -0.07
    ads
    -0.06
     Observation
    -0.06
    ᛐ
    -0.06
    POSITIVE LOGITS
     GMO
    0.07
     Commod
    0.07
     Marcel
    0.07
    roman
    0.07
     Employee
    0.07
    aryawan
    0.07
    <Base
    0.06
    _STAR
    0.06
    -wheel
    0.06
    生产车间
    0.06
    Act Density 0.013%

    No Known Activations