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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ett
    1.20
    一个
    0.94
     Ett
    0.92
    三個
    0.90
    兩個
    0.85
    一個
    0.83
    第二个
    0.82
    三个
    0.81
     два
    0.80
    第一个
    0.79
    POSITIVE LOGITS
     una
    1.89
     uma
    1.81
     Una
    1.77
    Una
    1.75
    Uma
    1.55
     Uma
    1.50
     Eine
    1.48
     eine
    1.46
     une
    1.45
    una
    1.43
    Act Density 0.001%

    No Known Activations