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

    Neuronpedia

    INDEX
    Explanations

    transition words followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     illetve
    0.20
     そして
    0.18
    そして
    0.18
     然後
    0.18
    িসহ
    0.18
    又は
    0.18
     হইয়৷
    0.17
     ponds
    0.17
    所以我
    0.17
     /$
    0.17
    POSITIVE LOGITS
    ،
    0.41
    ,
    0.41
    ၊
    0.36
    ，
    0.36
    、
    0.31
    ፣
    0.26
     ،
    0.23
    ,,
    0.23
    :
    0.23
    ؛
    0.23
    Act Density 2.877%

    No Known Activations