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

    Neuronpedia

    INDEX
    Explanations

    trained on data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Categoria
    0.50
    ம்
    0.45
    ता
    0.44
    ատ
    0.44
     добавля
    0.42
    Ꮘ
    0.41
    িষ্ট
    0.41
    EVEN
    0.40
    גם
    0.40
    ശേഷ
    0.40
    POSITIVE LOGITS
     paham
    0.44
     adversity
    0.42
     violencia
    0.41
     upbringing
    0.41
     watersheds
    0.40
     textbooks
    0.40
     peacetime
    0.40
     totalitarian
    0.39
    confined
    0.39
    observ
    0.39
    Act Density 0.085%

    No Known Activations