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

    Neuronpedia

    INDEX
    Explanations

    I, me, my, myself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amaç
    1.05
     zna
    0.95
     tráfico
    0.93
     পাকা
    0.92
    也很
    0.90
    疑問
    0.89
     podrá
    0.87
     علاق
    0.87
     darse
    0.87
     重量
    0.86
    POSITIVE LOGITS
     myself
    1.02
     Myself
    0.92
     করিতেছি
    0.83
     depicting
    0.75
     tick
    0.75
    My
    0.73
    રિક
    0.71
     advancing
    0.71
     personally
    0.69
     делаю
    0.69
    Act Density 0.755%

    No Known Activations