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

    Neuronpedia

    INDEX
    Explanations

    br en world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mapping
    0.45
    फिट
    0.45
    evaluate
    0.44
    ownicy
    0.44
    rational
    0.43
    fits
    0.43
     तूती
    0.43
    modulo
    0.43
     Texto
    0.42
    فيق
    0.41
    POSITIVE LOGITS
     balcony
    0.46
     drone
    0.44
     ब्रिटिश
    0.44
     té
    0.43
     British
    0.43
     department
    0.42
     PAY
    0.42
     terraces
    0.42
     purchase
    0.41
     dinner
    0.41
    Act Density 0.005%

    No Known Activations