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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    汀
    -0.07
    勚
    -0.07
    쑝
    -0.07
    さらに
    -0.07
     UITableView
    -0.07
    UserData
    -0.07
     Holly
    -0.07
     yü
    -0.06
    udded
    -0.06
     ürün
    -0.06
    POSITIVE LOGITS
     original
    0.09
    经营
    0.08
    商店
    0.08
    PECIAL
    0.08
     raison
    0.07
    Considering
    0.07
    -supported
    0.07
     Mob
    0.07
     prob
    0.07
    Ideal
    0.07
    Act Density 0.004%

    No Known Activations