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

    Neuronpedia

    INDEX
    Explanations

    references to parks and trails, specifically their locations and connections

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

    Prepositions preceding locations

    np_acts-logits-general · gemini-2.0-flash

    city names and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Notting
    -0.60
     Abuja
    -0.59
     Warszawie
    -0.59
     Lagos
    -0.58
     Krakowie
    -0.58
     Malibu
    -0.56
    Toronto
    -0.55
     CHICAGO
    -0.55
     Toronto
    -0.55
     Bucharest
    -0.55
    POSITIVE LOGITS
     city
    0.97
    city
    0.79
     City
    0.77
    City
    0.77
    CITY
    0.76
     CITY
    0.72
     città
    0.64
     város
    0.63
     städ
    0.62
     ciudad
    0.59
    Act Density 0.156%

    No Known Activations