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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of countries, cities, and notable figures

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

    countries and cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ertale
    -0.49
    IntoConstraints
    -0.48
    -0.47
    OGND
    -0.46
    enderror
    -0.45
    ərbaycan
    -0.45
     nakalista
    -0.43
    delwed
    -0.43
    gdx
    -0.43
     BorderSide
    -0.42
    POSITIVE LOGITS
    Havolalar
    0.54
     nahilalakip
    0.52
     Administrativna
    0.52
     Мексичка
    0.42
    stdio
    0.41
     PHOTOS
    0.40
     TECHNOLOGIES
    0.40
     caucho
    0.40
    kamers
    0.40
    Gemeinden
    0.39
    Act Density 0.063%

    No Known Activations