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

    Neuronpedia

    INDEX
    Explanations

    areas to stay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hotel
    2.16
     Hotel
    1.85
    hotel
    1.85
     HOTEL
    1.80
     होटल
    1.80
    Hotel
    1.79
    酒店
    1.77
     호텔
    1.75
    ホテル
    1.69
     hotels
    1.66
    POSITIVE LOGITS
     stayed
    0.54
    stay
    0.53
     staying
    0.48
     stay
    0.46
    停
    0.45
    停留
    0.42
    Stay
    0.42
     रहना
    0.40
     останови
    0.40
     STAY
    0.40
    Act Density 0.003%

    No Known Activations