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

    Neuronpedia

    INDEX
    Explanations

    clauses ending in commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     although
    0.47
    よりも
    0.47
     wobei
    0.46
     tetapi
    0.44
     albeit
    0.43
     ebenso
    0.43
     meski
    0.42
    കൊണ്ട്
    0.42
     aunque
    0.41
    although
    0.41
    POSITIVE LOGITS
    ،
    1.02
    ，
    1.00
    ,
    0.91
    ၊
    0.74
    ,,
    0.68
    ፣
    0.66
    ‌,
    0.64
    $,
    0.63
     ،
    0.62
     ፣
    0.61
    Act Density 0.049%

    No Known Activations