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

    Neuronpedia

    INDEX
    Explanations

    references to specific buildings and architectural elements

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

    buildings and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.63
     kaarangay
    -0.56
    ConfigureAwait
    -0.54
    afficheront
    -0.52
     mergeFrom
    -0.52
     PeEnEo
    -0.51
    Chham
    -0.51
     pinulongan
    -0.51
    Diwedd
    -0.50
     InputDecoration
    -0.50
    POSITIVE LOGITS
     buildings
    0.79
     building
    0.75
     Buildings
    0.66
    Buildings
    0.65
    buildings
    0.65
     Building
    0.64
    building
    0.63
     Gebäude
    0.60
     bâtiment
    0.60
    Building
    0.60
    Act Density 0.074%

    No Known Activations