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

    Neuronpedia

    INDEX
    Explanations

    step-by-step instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.77
     Perpetual
    0.76
    ermo
    0.76
    ectomy
    0.74
    岐
    0.73
     glory
    0.73
    eterminate
    0.73
    ering
    0.72
    fishing
    0.72
    uraea
    0.71
    POSITIVE LOGITS
     पादु
    0.93
    丁寧に
    0.91
     خلف
    0.90
     awal
    0.89
    weise
    0.88
     shí
    0.87
     নেতৃত্ব
    0.86
     বিপরীতে
    0.86
    を踏
    0.85
     بد
    0.85
    Act Density 0.120%

    No Known Activations