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

    Neuronpedia

    INDEX
    Explanations

    questions and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    説明
    0.44
    mbr
    0.44
     будем
    0.43
     helps
    0.43
    author
    0.43
     acids
    0.43
     explicação
    0.42
    ନ୍
    0.41
    ises
    0.41
     መል
    0.41
    POSITIVE LOGITS
    侨
    0.49
    غيرة
    0.46
     bungal
    0.43
    🏙
    0.43
     நகரம்
    0.40
    但是在
    0.40
     yıldır
    0.39
    果然
    0.39
     ഓഫ്
    0.39
    昼
    0.39
    Act Density 0.005%

    No Known Activations