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

    Neuronpedia

    INDEX
    Explanations

    references to cities and urban locations

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

    "City"

    np_acts-logits-general · gemini-2.0-flash

    city of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     themſelves
    -0.96
     myſelf
    -0.93
    ✨:
    -0.81
    Искәрмәләр
    -0.80
     AssemblyCompany
    -0.79
     ſeveral
    -0.77
    UrlResolution
    -0.76
     ویکی‌پدی
    -0.75
     domésticos
    -0.74
     mariée
    -0.73
    POSITIVE LOGITS
     City
    0.99
     cities
    0.98
     city
    0.96
     CITY
    0.90
     Cities
    0.89
     getCity
    0.88
    City
    0.84
    city
    0.84
    CITY
    0.79
    wide
    0.78
    Act Density 0.109%

    No Known Activations