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

    Neuronpedia

    INDEX
    Explanations

    adult contexts and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    1.22
     i
    0.91
     e
    0.80
    Ó
    0.78
    小组
    0.77
    માં
    0.77
     স
    0.74
    錶
    0.73
     argued
    0.72
    在
    0.72
    POSITIVE LOGITS
    adult
    1.10
     Adult
    1.08
     adulta
    1.06
     adults
    1.05
     взрослых
    1.04
    ن
    1.03
    น
    1.02
    <0x80>
    1.00
     Adults
    0.98
    t
    0.98
    Act Density 0.012%

    No Known Activations