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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and names

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

    Locations (cities, regions, countries)

    np_acts-logits-general · gemini-2.0-flash

    international locations and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Universitaria
    -0.46
    itares
    -0.41
     pseud
    -0.41
     meja
    -0.41
    Route
    -0.40
    rough
    -0.39
     desnuda
    -0.39
    madol
    -0.39
    cesta
    -0.39
    Jeux
    -0.37
    POSITIVE LOGITS
     overseas
    0.68
     abroad
    0.61
     Overseas
    0.59
     Abroad
    0.54
    StoryboardSegue
    0.52
    overse
    0.52
     Мексичка
    0.51
    Overseas
    0.51
    EndGlobalSection
    0.50
    rrggbb
    0.49
    Act Density 0.571%

    No Known Activations