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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographical locations and their societal contexts

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

    Capital cities or related terms

    np_acts-logits-general · gemini-2.0-flash

    capital cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ритори
    -0.63
    ächs
    -0.56
     Pyrenees
    -0.51
    hamshire
    -0.51
     mallorca
    -0.49
     Derbyshire
    -0.49
     uruguay
    -0.49
     pat
    -0.49
     Shropshire
    -0.48
    GeneratedValue
    -0.48
    POSITIVE LOGITS
     cities
    0.86
     Cities
    0.79
     metropolis
    0.76
     ciudades
    0.74
     Hauptstadt
    0.72
     capitale
    0.70
    MLLoader
    0.69
     capitales
    0.69
     huvud
    0.67
    yntaxException
    0.67
    Act Density 0.227%

    No Known Activations