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

    Neuronpedia

    INDEX
    Explanations

    Considerations section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    파일명
    0.36
     lifestyles
    0.36
     препарат
    0.35
     fondamental
    0.35
     مشکل
    0.35
    ClassObject
    0.35
     constituencies
    0.34
     urząd
    0.33
     ಸಂಬ
    0.33
     मुख्य
    0.33
    POSITIVE LOGITS
     section
    1.70
     kısm
    1.38
    部分
    1.32
     portion
    1.27
    section
    1.27
     kısmı
    1.25
     bölüm
    1.23
     sección
    1.21
     부분이
    1.18
     часть
    1.16
    Act Density 0.084%

    No Known Activations