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

    Neuronpedia

    INDEX
    Explanations

    between and among

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fehl
    0.36
     অধিকাংশই
    0.35
     för
    0.33
     agrade
    0.33
     für
    0.33
     Suz
    0.33
     sofern
    0.33
     beliebt
    0.33
     airson
    0.32
     além
    0.32
    POSITIVE LOGITS
     між
    0.68
    彼此
    0.67
     между
    0.65
     서로
    0.64
     birbir
    0.63
    Between
    0.60
    同士
    0.60
     μεταξύ
    0.59
    між
    0.59
    互相
    0.58
    Act Density 0.461%

    No Known Activations