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

    Neuronpedia

    INDEX
    Explanations

    still under

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.50
     already
    0.48
     FileManager
    0.48
    cosity
    0.47
    dish
    0.46
    gency
    0.46
     newest
    0.46
    :
    0.46
     aina
    0.45
    enstein
    0.44
    POSITIVE LOGITS
     fortfarande
    0.67
     still
    0.60
     هنوز
    0.59
    まだまだ
    0.59
    仍然
    0.57
    仍
    0.56
     остается
    0.55
    まだ
    0.55
     todavía
    0.54
    尚未
    0.54
    Act Density 0.065%

    No Known Activations