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

    Neuronpedia

    INDEX
    Explanations

    difference between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    与之
    0.45
    跟他
    0.42
     contraire
    0.40
    跟你
    0.39
     eigenen
    0.37
    ابعه
    0.36
    跟我
    0.36
    娲
    0.35
     seiner
    0.35
     অধিকাংশই
    0.34
    POSITIVE LOGITS
     between
    2.69
     между
    2.55
     між
    2.50
    between
    2.38
     بين
    2.33
     zwischen
    2.30
     Between
    2.28
     tussen
    2.28
    Between
    2.25
     giữa
    2.25
    Act Density 0.085%

    No Known Activations