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

    Neuronpedia

    INDEX
    Explanations

    seemingly followed by adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ме
    1.28
    ع
    1.08
    д
    1.01
    ların
    0.98
     ﺍ
    0.94
     Nó
    0.94
     rapides
    0.93
    បញ្ចូល
    0.90
    F
    0.90
     tasmim
    0.89
    POSITIVE LOGITS
    ओं
    1.18
    4
    1.06
    5
    1.00
    .’
    0.97
    ა
    0.94
    .
    0.91
    ের
    0.90
    (
    0.90
     veteran
    0.88
    ena
    0.86
    Act Density 0.014%

    No Known Activations