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

    Neuronpedia

    INDEX
    Explanations

    product or quotient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ありません
    1.54
    ق
    1.45
    h
    1.41
     mẽ
    1.38
    ه
    1.37
    iances
    1.34
    યા
    1.33
    ким
    1.30
    िल
    1.29
    یا
    1.24
    POSITIVE LOGITS
     спокойно
    1.75
     disso
    1.74
    ed
    1.71
    ت
    1.60
    ate
    1.59
     pierwsze
    1.59
    eer
    1.57
     amoureux
    1.56
    ள்ளதாக
    1.53
    ATE
    1.52
    Act Density 0.054%

    No Known Activations