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

    Neuronpedia

    INDEX
    Explanations

    references to specific cities and their characteristics

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

    preceding names of cities or capitals

    np_acts-logits-general · gemini-2.0-flash

    major cities and capitals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     церковь
    -0.45
     церкви
    -0.43
     
    -0.43
     조
    -0.42
    文庫
    -0.41
    vo
    -0.41
    조
    -0.41
    ,
    -0.40
    <eos>
    -0.40
     fatta
    -0.40
    POSITIVE LOGITS
     city
    1.98
     cities
    1.61
     CITY
    1.60
    city
    1.59
     City
    1.58
     metropolis
    1.49
     capital
    1.49
    CITY
    1.49
    City
    1.48
     getCity
    1.41
    Act Density 0.126%

    No Known Activations