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

    Neuronpedia

    INDEX
    Explanations

    activities and excursions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whitespace
    0.82
    computing
    0.75
     operands
    0.75
     computational
    0.72
    ニュアル
    0.71
     computing
    0.71
     تكعيب
    0.71
    Computation
    0.70
     reactants
    0.70
     Computation
    0.70
    POSITIVE LOGITS
     tours
    1.99
     tour
    1.94
     Tours
    1.63
     sightseeing
    1.58
     itinerary
    1.57
     Tour
    1.56
     excursion
    1.54
     excursions
    1.52
    Tour
    1.47
     guided
    1.42
    Act Density 0.632%

    No Known Activations