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

    Neuronpedia

    INDEX
    Explanations

    lieutenant general

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     daughter
    0.62
    daughter
    0.58
     Daughter
    0.51
     son
    0.49
     brother
    0.48
    女儿
    0.48
    brother
    0.48
     Tochter
    0.46
     hermana
    0.45
    息子
    0.45
    POSITIVE LOGITS
     colonel
    0.77
    Colonel
    0.68
     Colonel
    0.67
     কর্নেল
    0.59
     কমান্ডার
    0.51
     admiral
    0.51
    Lieutenant
    0.46
     জেনারেল
    0.44
     lieutenant
    0.44
     जनरल
    0.44
    Act Density 0.002%

    No Known Activations