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

    Neuronpedia

    INDEX
    Explanations

    foreign punctuation and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ח
    0.73
     Algonquin
    0.66
     American
    0.64
     can
    0.61
     Up
    0.59
     Brownian
    0.59
     Database
    0.58
     Connecticut
    0.58
     Louvre
    0.58
     Colombian
    0.57
    POSITIVE LOGITS
    ，
    0.88
     và
    0.87
    ،
    0.82
     esclusivamente
    0.81
     effettu
    0.79
     και
    0.79
     în
    0.78
     già
    0.77
     tidligere
    0.77
     étaient
    0.77
    Act Density 4.084%

    No Known Activations