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

    Neuronpedia

    INDEX
    Explanations

    descriptive labels before colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kten
    0.48
     miserable
    0.44
     sterile
    0.39
     swollen
    0.39
     이미지
    0.39
     wretched
    0.39
     ಅವನ
    0.39
     infr
    0.39
     helpless
    0.38
     Wallis
    0.38
    POSITIVE LOGITS
    École
    0.47
    Université
    0.42
     États
    0.39
    вшая
    0.38
     দিয়েছেন
    0.36
    دأ
    0.36
     Admission
    0.35
    QMainWindow
    0.34
     telah
    0.34
     Université
    0.34
    Act Density 0.003%

    No Known Activations