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

    Neuronpedia

    INDEX
    Explanations

    references to physical locations or spaces, specifically rooms

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

    "room" or "rooms"

    np_acts-logits-general · gemini-2.0-flash

    room temperature or air

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )";
    -0.87
    )');
    -0.85
    </tfoot>
    -0.82
    %]
    -0.79
    )";
    -0.79
    ')));
    -0.79
    %")
    -0.78
    startAnimation
    -0.77
    )»
    -0.77
    ]';
    -0.75
    POSITIVE LOGITS
     Room
    1.30
     rooms
    1.27
     Rooms
    1.24
     ROOM
    1.18
     room
    1.17
    Rooms
    1.15
    Room
    1.15
    rooms
    1.07
    ROOM
    0.99
    room
    0.97
    Act Density 0.050%

    No Known Activations