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

    Neuronpedia

    INDEX
    Explanations

    geographic locations, particularly cities

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

    city names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.72
     transfieras
    -0.63
    :+:
    -0.60
    Derbyniad
    -0.56
    Personendaten
    -0.54
     propOrder
    -0.50
     Paglinawan
    -0.49
    +#+
    -0.49
    #+#
    -0.45
    ArgsConstructor
    -0.45
    POSITIVE LOGITS
     Islamabad
    0.57
     Nairobi
    0.54
     Auckland
    0.54
     Abuja
    0.54
     Canberra
    0.52
    Milwaukee
    0.52
     Melbourne
    0.52
     Brooklyn
    0.51
     Amsterdam
    0.50
     Milwaukee
    0.50
    Act Density 0.014%

    No Known Activations