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

    Neuronpedia

    INDEX
    Explanations

    technical documentation and planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     اهمیت
    0.47
     முன்ப
    0.46
     약
    0.44
     sarees
    0.44
     ኢ
    0.44
     বিভিন্ন
    0.44
     인한
    0.43
    ین
    0.43
     약간
    0.42
     વિવિધ
    0.42
    POSITIVE LOGITS
    ت
    0.50
     Blot
    0.50
     secolo
    0.48
    т
    0.48
    乸
    0.47
    лкой
    0.44
    on
    0.44
    نوان
    0.44
     planeta
    0.44
    sø
    0.43
    Act Density 0.000%

    No Known Activations