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

    Neuronpedia

    INDEX
    Explanations

    building on information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    特に
    0.50
     특히
    0.45
     Đặc
    0.44
    their
    0.42
     الكت
    0.42
    류
    0.41
    ⵔ
    0.41
    tter
    0.41
    悭
    0.40
    十分に
    0.40
    POSITIVE LOGITS
     informa
    0.48
     modific
    0.47
     information
    0.47
     alap
    0.47
     differ
    0.45
     realities
    0.44
     recalls
    0.44
     aliment
    0.44
     multimedia
    0.44
     emotional
    0.43
    Act Density 0.009%

    No Known Activations