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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     и
    2.23
     และ
    2.22
     and
    2.16
    和
    2.09
    และ
    2.03
    and
    2.01
     এবং
    1.98
     και
    1.95
     和
    1.92
     và
    1.90
    POSITIVE LOGITS
     accordingly
    1.77
     correspondingly
    1.66
     consequently
    1.45
    はその
    1.44
     therein
    1.41
    它可以
    1.36
    ائها
    1.32
     derfor
    1.28
     یې
    1.27
     hopefully
    1.25
    Act Density 0.405%

    No Known Activations