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

    Neuronpedia

    INDEX
    Explanations

    sequencing Roman numerals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     இசை
    0.42
     aire
    0.40
    টো
    0.39
     editar
    0.38
     actual
    0.37
    Ore
    0.37
    aree
    0.37
    Editar
    0.37
    ენა
    0.37
     permanente
    0.37
    POSITIVE LOGITS
     شروع
    0.42
     sincerely
    0.39
    Recovery
    0.38
     recovery
    0.37
    读书
    0.37
     bại
    0.37
    antas
    0.36
    водства
    0.35
     Recovery
    0.35
    дал
    0.35
    Act Density 0.000%

    No Known Activations