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

    Neuronpedia

    INDEX
    Explanations

    applied using

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    аз
    0.43
     elusive
    0.43
    excluding
    0.42
     appet
    0.41
     aşağı
    0.41
    ασίας
    0.40
     daripada
    0.40
    azepam
    0.39
     uchun
    0.39
     placements
    0.39
    POSITIVE LOGITS
    很久
    0.44
     스스로
    0.43
    公路
    0.42
     hashing
    0.41
     시작
    0.40
     Gothenburg
    0.40
     البدايه
    0.39
    FactoryBean
    0.39
    広く
    0.38
     independently
    0.38
    Act Density 0.009%

    No Known Activations