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

    Neuronpedia

    INDEX
    Explanations

    because / due to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Всем
    0.46
    З
    0.45
    ли
    0.45
     ailing
    0.44
    ﻌ
    0.43
    М
    0.43
    е
    0.42
    ల
    0.42
     troubled
    0.42
    Всім
    0.42
    POSITIVE LOGITS
     lhs
    0.47
     nella
    0.47
    由于
    0.47
     图
    0.46
     deoarece
    0.46
    🧤
    0.45
     aufgrund
    0.45
    🎳
    0.45
     поскольку
    0.44
     zgodnie
    0.44
    Act Density 0.003%

    No Known Activations