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

    Neuronpedia

    INDEX
    Explanations

    UML diagrams and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    戻る
    -1.55
    這些
    -1.47
    Estos
    -1.45
    Asimismo
    -1.45
    tiglia
    -1.41
     海报
    -1.38
     These
    -1.35
    土曜日
    -1.35
     interieur
    -1.35
    יצוב
    -1.33
    POSITIVE LOGITS
    </h2>
    2.00
    :
    1.41
     
    1.30
    0
    1.27
    id
    1.27
     Noviembre
    1.26
     samo
    1.25
     Septiembre
    1.23
    A
    1.22
    O
    1.22
    Act Density 0.007%

    No Known Activations