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

    Neuronpedia

    INDEX
    Explanations

    references to major cities and their characteristics

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

    Cities

    np_acts-logits-general · gemini-2.0-flash

    major cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arusian
    -0.65
    genstein
    -0.62
    dération
    -0.62
     Perak
    -0.61
     Jharkhand
    -0.61
     Romagna
    -0.61
     Belarusian
    -0.61
     Eritrea
    -0.59
     Himachal
    -0.59
     Derbyshire
    -0.58
    POSITIVE LOGITS
     London
    1.03
     Paris
    0.92
     Tokyo
    0.89
    London
    0.89
     Madrid
    0.88
     Chicago
    0.87
     Berlin
    0.86
     Boston
    0.80
     Seoul
    0.79
     Londres
    0.78
    Act Density 0.327%

    No Known Activations