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

    Neuronpedia

    INDEX
    Explanations

    but and contrastive conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.24
    \",
    0.20
    、
    0.20
    ，
    0.19
    ፣
    0.18
     ئ
    0.18
          
    0.18
     L
    0.17
    \"
    0.17
    ↵
    0.17
    POSITIVE LOGITS
    but
    0.41
     लेकिन
    0.38
     but
    0.38
     nhưng
    0.37
    แต่
    0.32
     لكن
    0.32
     אבל
    0.31
     pero
    0.31
     কিন্তু
    0.31
     lakini
    0.30
    Act Density 0.234%

    No Known Activations