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

    Neuronpedia

    INDEX
    Explanations

    positive qualities for tools and technology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chaired
    0.42
     বিশ্বে
    0.40
     éxitos
    0.38
     völl
    0.37
     Arthritis
    0.37
     ખાતે
    0.37
     rápid
    0.37
     عدد
    0.36
     gratis
    0.35
    最好的
    0.35
    POSITIVE LOGITS
     ){
    0.33
    0.33
    าง
    0.32
    ופ
    0.31
     מג
    0.31
    ฏ
    0.31
    หย
    0.30
     ಸೂ
    0.29
    提及
    0.29
    킷
    0.29
    Act Density 0.024%

    No Known Activations