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

    Neuronpedia

    INDEX
    Explanations

    price ranges and percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.33
     bijna
    0.33
    iesią
    0.32
     aproape
    0.32
     almost
    0.30
     تقريبا
    0.29
     centena
    0.28
     około
    0.28
     nearly
    0.28
     quase
    0.28
    POSITIVE LOGITS
     weren
    0.22
     Gable
    0.22
    粡
    0.22
    驼
    0.22
     curated
    0.21
     Face
    0.21
    撸
    0.21
     إل
    0.21
    无
    0.20
    邝
    0.20
    Act Density 0.399%

    No Known Activations