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

    Neuronpedia

    INDEX
    Explanations

    sensitive to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ошибка
    0.66
     guideline
    0.63
     новый
    0.63
     procedimento
    0.63
     proposal
    0.60
     предложение
    0.59
     или
    0.59
     ή
    0.59
     ("/
    0.59
     requested
    0.58
    POSITIVE LOGITS
     nejen
    1.09
     മാത്രമല്ല
    0.96
    不仅仅
    0.95
     birçok
    0.95
     மட்டுமல்ல
    0.91
    เหล่านี้
    0.88
     훨씬
    0.87
     zarówno
    0.86
    many
    0.85
    許多
    0.85
    Act Density 0.002%

    No Known Activations