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

    Neuronpedia

    INDEX
    Explanations

    TripAdvisor and travel reviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    1.09
    ش
    0.88
    д
    0.66
    لى
    0.61
    دين
    0.57
    星
    0.57
    да
    0.55
    ب
    0.55
    تى
    0.55
    roll
    0.54
    POSITIVE LOGITS
     dipl
    0.69
     TripAdvisor
    0.66
     newsp
    0.65
    ON
    0.64
     Heming
    0.63
     Фран
    0.63
     i
    0.62
     osa
    0.62
     hereto
    0.61
    '
    0.61
    Act Density 0.000%

    No Known Activations