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

    Neuronpedia

    INDEX
    Explanations

    สรุปและเข้าใจ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tertentu
    0.84
     này
    0.83
     universitario
    0.79
     arasında
    0.79
     pued
    0.78
    を利用
    0.76
     considérable
    0.76
     olabilir
    0.76
     napraw
    0.76
    ចាយ
    0.75
    POSITIVE LOGITS
     những
    1.02
     các
    0.99
     việc
    0.83
     các
    0.79
     sự
    0.78
    การ
    0.60
     vai
    0.59
    ການ
    0.59
     một
    0.56
    các
    0.56
    Act Density 0.010%

    No Known Activations