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

    Neuronpedia

    INDEX
    Explanations

    age and life stages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ה
    0.34
    ও
    0.33
    ﻘ
    0.29
    들이
    0.29
    া
    0.29
    동
    0.28
    사의
    0.28
    ा
    0.27
    تح
    0.27
    ﺘ
    0.27
    POSITIVE LOGITS
    ant
    0.30
    '.
    0.29
    isation
    0.28
     adulte
    0.28
     incapable
    0.28
     minors
    0.27
    ,
    0.27
     adulta
    0.27
    ak
    0.26
    ad
    0.26
    Act Density 0.108%

    No Known Activations