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

    Neuronpedia

    INDEX
    Explanations

    references to geographic locations and specific place names

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

    after locations (cities, regions, etc.)

    np_acts-logits-general · gemini-2.0-flash

    Nissan models and place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sligo
    -0.75
     ujednoznacz
    -0.71
     <<<<<<<<<<<<<<
    -0.70
     Amarillo
    -0.68
     Inu
    -0.66
     Trumb
    -0.66
     Wade
    -0.66
     Shropshire
    -0.65
    lioma
    -0.64
     Tulsa
    -0.64
    POSITIVE LOGITS
     Brighton
    0.91
     Chesterfield
    0.89
     Sussex
    0.88
     Surrey
    0.85
    Brighton
    0.82
     Richmond
    0.79
     Chile
    0.78
    Chile
    0.77
    Sega
    0.74
    Surrey
    0.74
    Act Density 0.549%

    No Known Activations