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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roo
    -0.07
     pł
    -0.07
    _ue
    -0.07
     vess
    -0.06
    (Display
    -0.06
     tí
    -0.06
     paylaş
    -0.06
    /activity
    -0.06
     cuc
    -0.06
     Każdy
    -0.06
    POSITIVE LOGITS
    מדיה
    0.08
     elemento
    0.07
    cente
    0.07
    涪
    0.07
     באופן
    0.07
    ProductName
    0.07
    枣庄
    0.07
     Truck
    0.06
    琐
    0.06
    席卷
    0.06
    Act Density 0.002%

    No Known Activations