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

    Neuronpedia

    INDEX
    Explanations

    Day 1: Arrival

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hotels
    0.46
    โรงแรม
    0.46
     Hotel
    0.44
     hotel
    0.43
     Hotels
    0.42
    тового
    0.40
    宿泊
    0.40
    Hotel
    0.40
     hôtel
    0.39
     lodging
    0.38
    POSITIVE LOGITS
     എത്ത
    0.50
     మార్
    0.44
    ઝ
    0.43
     Афри
    0.41
     llegará
    0.40
     chega
    0.39
    Сер
    0.38
     الخميس
    0.38
     llegue
    0.38
    非洲
    0.38
    Act Density 0.001%

    No Known Activations