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

    Neuronpedia

    INDEX
    Explanations

    at the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dbus
    -0.07
    356
    -0.07
    باح
    -0.07
    حي
    -0.07
    MONTH
    -0.07
    .schedule
    -0.07
    _vehicle
    -0.06
    _encoded
    -0.06
    ant
    -0.06
     detalle
    -0.06
    POSITIVE LOGITS
    ìm
    0.07
     lze
    0.06
     leaned
    0.06
    仪
    0.06
     시
    0.06
     whipped
    0.06
    ньому
    0.06
    UICollectionView
    0.06
     �
    0.06
     intermediate
    0.06
    Act Density 0.019%

    No Known Activations