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

    Neuronpedia

    INDEX
    Explanations

    ancient history and civilizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MVC
    0.49
    hk
    0.48
     தனி
    0.48
     вет
    0.47
     sagging
    0.47
     家庭
    0.47
     CTE
    0.47
     chops
    0.46
     TV
    0.46
     HK
    0.46
    POSITIVE LOGITS
    منا
    0.45
    𝓉
    0.44
    Flagge
    0.43
    Ꮀ
    0.43
     fijn
    0.43
    커
    0.42
    𒄑
    0.42
    수
    0.42
    溇
    0.41
    overy
    0.41
    Act Density 0.013%

    No Known Activations