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

    Neuronpedia

    INDEX
    Explanations

    very + descriptive word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ancienne
    0.31
    کس
    0.30
     더욱
    0.29
     cuivre
    0.29
     środ
    0.29
    いた
    0.29
     supérieur
    0.28
     juin
    0.27
     víctima
    0.27
    ِی
    0.27
    POSITIVE LOGITS
    at
    0.41
    es
    0.36
    ley
    0.36
    to
    0.36
    em
    0.34
    .
    0.34
    et
    0.33
    al
    0.31
    ed
    0.30
    ledes
    0.30
    Act Density 0.187%

    No Known Activations