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

    Neuronpedia

    INDEX
    Explanations

    one, two, one, two, one, an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iduría
    0.87
    жливо
    0.84
    取り組み
    0.82
    ທີ່ມີ
    0.78
     genutzt
    0.77
    ITECT
    0.76
    anfaatkan
    0.76
    了好
    0.76
    を活用
    0.76
    iritual
    0.75
    POSITIVE LOGITS
    1.30
     are
    1.05
     can
    1.02
     is
    0.99
     two
    0.99
     one
    0.97
    一个
    0.96
     will
    0.90
     eine
    0.90
     respondents
    0.89
    Act Density 3.572%

    No Known Activations