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

    Neuronpedia

    INDEX
    Explanations

    adverbs and participles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ually
    0.59
    적으로
    0.54
    的に
    0.50
    ALLY
    0.48
    的な
    0.47
    iczne
    0.47
    完全
    0.47
    ally
    0.46
    ially
    0.45
     totalmente
    0.45
    POSITIVE LOGITS
     loudly
    0.56
     wist
    0.55
     calmly
    0.50
     quietly
    0.50
     steadily
    0.49
     magnific
    0.48
     loud
    0.47
     plaint
    0.47
     anxiously
    0.45
     warmly
    0.45
    Act Density 0.006%

    No Known Activations