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

    Neuronpedia

    INDEX
    Explanations

    overlooking the city

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ayer
    0.45
     dibujar
    0.42
     miserable
    0.40
    ığın
    0.40
     capricious
    0.40
    ウス
    0.39
    idden
    0.39
    <0xA8>
    0.38
    Imagen
    0.38
     scarcely
    0.38
    POSITIVE LOGITS
     Flooring
    0.49
     ইঞ্জিনিয়ার
    0.45
     সেক্ট
    0.45
     Fittings
    0.44
     Soils
    0.43
    皰
    0.42
     сосу
    0.41
     і
    0.41
     तयारी
    0.40
    മ്മ
    0.40
    Act Density 0.001%

    No Known Activations