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

    Neuronpedia

    INDEX
    Explanations

    hotel amenities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bali
    0.41
    uksi
    0.38
     paradise
    0.37
    Mét
    0.37
    হো
    0.36
    र्‍या
    0.36
    LOGIN
    0.36
    حم
    0.36
    我們要
    0.36
    ్రమ
    0.36
    POSITIVE LOGITS
     retained
    0.39
     miễn
    0.39
     moved
    0.38
     investigated
    0.37
     inoltre
    0.36
    WeekDates
    0.36
     Detalles
    0.36
     देवेंद्र
    0.35
    excludeFolder
    0.35
     hac
    0.35
    Act Density 0.001%

    No Known Activations