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

    Neuronpedia

    INDEX
    Explanations

    conjunctions in many languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ri
    0.21
    ut
    0.21
     तीन
    0.21
    IA
    0.20
    สุด
    0.20
    แรม
    0.20
     forego
    0.20
    у
    0.20
    ’
    0.20
     onion
    0.20
    POSITIVE LOGITS
    dır
    0.26
    이며
    0.25
     και
    0.25
     и
    0.23
     și
    0.23
     மற்றும்
    0.23
    дных
    0.22
    সহ
    0.22
     ও
    0.22
     અને
    0.22
    Act Density 0.000%

    No Known Activations