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

    Neuronpedia

    INDEX
    Explanations

    references to specific places, particularly houses or establishments

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

    words for house

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Timoteo
    -0.46
    nología
    -0.45
     Obrigado
    -0.44
     atún
    -0.44
    yente
    -0.43
     Moyen
    -0.43
    Географиясе
    -0.42
     Irish
    -0.42
     pointless
    -0.42
     griech
    -0.41
    POSITIVE LOGITS
    Casa
    2.06
     Casa
    2.02
     casa
    1.66
    casa
    1.62
     CASA
    1.55
    CASA
    1.52
     casas
    1.20
     Casas
    1.06
     Maison
    0.94
     HOUSE
    0.93
    Act Density 0.002%

    No Known Activations