INDEX
    Explanations

    The neuron activates on words that refer to tourism and travel—especially mentions of visitors, tourists, tours, and related travel‐activity terms.

    New Auto-Interp
    Negative Logits
    Tek
    -0.07
     레이
    -0.06
    -0.06
    ('./
    -0.06
    .wordpress
    -0.06
    rvé
    -0.06
     yup
    -0.06
    nis
    -0.06
     následující
    -0.06
    -0.06
    POSITIVE LOGITS
    "class
    0.06
    pillar
    0.06
     draggable
    0.06
     AssetImage
    0.06
    Australian
    0.06
     нед
    0.06
     prendre
    0.06
    $class
    0.06
     dağ
    0.06
     действия
    0.06
    Act Density 0.059%

    No Known Activations