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

    Neuronpedia

    INDEX
    Explanations

    understand you / could you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yo
    0.82
    He
    0.79
     y
    0.79
    You
    0.79
     You
    0.78
    Would
    0.77
    We
    0.77
     Would
    0.77
     He
    0.76
    They
    0.73
    POSITIVE LOGITS
     scelto
    0.74
    カフェ
    0.72
     Бел
    0.72
     nobis
    0.72
    🇦
    0.72
     deix
    0.71
     punctu
    0.70
     ইন্টারন্যাশনাল
    0.69
     alguma
    0.69
    ِل
    0.69
    Act Density 0.011%

    No Known Activations