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

    Neuronpedia

    INDEX
    Explanations

    specific formality levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     අපි
    0.52
    😛
    0.49
    Ideally
    0.46
    зию
    0.46
     นอกจาก
    0.45
    齐全
    0.45
    ,…
    0.45
     सोडा
    0.45
    さと
    0.45
    uyorum
    0.45
    POSITIVE LOGITS
     registration
    0.42
     mantle
    0.41
     registering
    0.40
    ওলানা
    0.40
    يريا
    0.40
     officials
    0.39
     pruebas
    0.39
     brief
    0.39
     preliminary
    0.39
     auditors
    0.39
    Act Density 0.002%

    No Known Activations