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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases about houses and their characteristics

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

    building descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Вы
    -0.31
     virtually
    -0.30
     звер
    -0.30
     parti
    -0.29
     avsl
    -0.28
     working
    -0.28
     mis
    -0.28
    GLenum
    -0.28
     trở
    -0.28
     pla
    -0.28
    POSITIVE LOGITS
     house
    1.45
     houſe
    1.31
     houses
    1.31
     Houſe
    1.28
    Houses
    1.20
     Houses
    1.18
    House
    1.16
     House
    1.14
     HOUSE
    1.14
    house
    1.13
    Act Density 0.063%

    No Known Activations