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

    Neuronpedia

    INDEX
    Explanations

    references to cities and towns

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

    city and town

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kissen
    -0.52
     traseiro
    -0.49
    sliding
    -0.49
     Noruega
    -0.49
     CSIRO
    -0.49
    InjectMocks
    -0.48
    enerbah
    -0.47
    casila
    -0.47
    flü
    -0.46
     MARTIN
    -0.46
    POSITIVE LOGITS
     city
    1.52
    City
    1.37
     City
    1.37
     town
    1.31
     cities
    1.23
    city
    1.21
     getCity
    1.13
     ciudad
    1.11
     Town
    1.09
    getCity
    1.08
    Act Density 0.033%

    No Known Activations