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

    Neuronpedia

    INDEX
    Explanations

    celebrating Thrones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     because
    0.51
     wavelengths
    0.46
     modality
    0.46
     untold
    0.45
     waves
    0.45
     camera
    0.45
     entire
    0.45
     rays
    0.44
     springs
    0.44
    \'
    0.44
    POSITIVE LOGITS
     проекты
    0.51
    糉
    0.51
     библиотека
    0.48
     рэгістрацыі
    0.47
     мебель
    0.46
    Furniture
    0.46
    Despatx
    0.46
    探讨
    0.46
     книга
    0.45
    Concluding
    0.45
    Act Density 0.020%

    No Known Activations