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

    Neuronpedia

    INDEX
    Explanations

    Last names following Jeff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     આવ્યા
    0.46
    واری
    0.43
    ức
    0.42
     ተግባ
    0.41
    యితే
    0.41
    saan
    0.40
    এখানে
    0.40
    variables
    0.39
    meed
    0.39
     अमाउंट
    0.39
    POSITIVE LOGITS
    reys
    0.64
     Bezos
    0.64
    rey
    0.55
     rey
    0.54
    REY
    0.52
    erson
    0.51
     subsid
    0.49
    ry
    0.49
     Jeff
    0.49
     jeff
    0.48
    Act Density 0.002%

    No Known Activations