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

    Neuronpedia

    INDEX
    Explanations

    lists followed by etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ale
    0.54
    டும்ப
    0.50
     Casino
    0.49
    van
    0.49
    only
    0.49
    ren
    0.48
     behest
    0.48
    wegian
    0.47
    one
    0.47
    ونکي
    0.47
    POSITIVE LOGITS
     ইত্যাদি
    0.72
     тощо
    0.70
     등이
    0.69
     itd
    0.64
     usw
    0.63
    等等
    0.61
     وغیرہ
    0.59
     دو
    0.59
     etc
    0.59
     등으로
    0.58
    Act Density 2.446%

    No Known Activations