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

    Neuronpedia

    INDEX
    Explanations

    AI

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TestMethod
    0.58
     ক্ষত্র
    0.52
    狞
    0.49
    Registration
    0.49
     கலோர
    0.49
     mvn
    0.48
     usp
    0.48
    ཛ
    0.48
    Proguard
    0.47
    韬
    0.47
    POSITIVE LOGITS
     AI
    3.06
    AI
    2.70
     ai
    2.34
     Ai
    2.14
    人工智能
    2.14
     artificial
    1.96
     Artificial
    1.91
    Ai
    1.91
    Artificial
    1.80
    ai
    1.80
    Act Density 1.328%

    No Known Activations