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

    Neuronpedia

    INDEX
    Explanations

    hotel names and brands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     理
    0.76
     მოს
    0.67
     ইনস্ট
    0.67
     לפ
    0.65
    osoma
    0.65
     setae
    0.64
     योगदान
    0.63
     الآ
    0.63
    妄
    0.62
     density
    0.62
    POSITIVE LOGITS
     Holiday
    1.45
    Holiday
    1.39
     Days
    1.16
     Hampton
    1.09
     Embassy
    1.09
     Quality
    1.03
    Days
    1.02
     holiday
    1.02
     Wyndham
    1.01
     Best
    1.00
    Act Density 0.013%

    No Known Activations