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

    Neuronpedia

    INDEX
    Explanations

    class declarations and related keywords in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Kotlin property declarations

    np_acts-logits-general · gemini-2.0-flash

    Canadian cities and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.55
     AssemblyProduct
    -0.52
     lượt
    -0.51
    CppMethod
    -0.51
    万美元
    -0.49
    £
    -0.46
     DBNull
    -0.45
    Symfony
    -0.44
    œ
    -0.44
    مرار
    -0.44
    POSITIVE LOGITS
     Canadians
    0.91
     Canada
    0.90
     CANADA
    0.88
    Canada
    0.86
     Ottawa
    0.86
     Calgary
    0.86
     Winnipeg
    0.85
     Edmonton
    0.85
    nipeg
    0.85
    tréal
    0.84
    Act Density 0.183%

    No Known Activations