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

    Neuronpedia

    INDEX
    Explanations

    cities and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suburban
    -0.13
     neighborhood
    -0.11
     Neighborhood
    -0.11
     homeland
    -0.11
    insula
    -0.11
    realm
    -0.10
     neighbourhood
    -0.09
    =@"
    -0.09
     Territories
    -0.09
    bote
    -0.09
    POSITIVE LOGITS
     cities
    0.52
     city
    0.46
     Cities
    0.40
    åŁİå¸Ĥ
    0.35
    cities
    0.35
    Cities
    0.34
     cittÃł
    0.34
    city
    0.31
     cidade
    0.30
     гоÑĢода
    0.29
    Act Density 0.119%

    No Known Activations