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

    Neuronpedia

    INDEX
    Explanations

    rooms

    np_max-act · gemini-2.0-flash

    mentions of hotel accommodation units—rooms and suites—especially their counts and descriptive details.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Negative Logits
     menget
    -0.09
    enter
    -0.09
    adini
    -0.08
     Enter
    -0.08
    Ingrese
    -0.08
    enteri
    -0.08
    coe
    -0.08
    Enter
    -0.08
    endo
    -0.08
    Dispose
    -0.08
    POSITIVE LOGITS
     chambres
    0.11
     spacious
    0.10
     cabins
    0.10
     guestrooms
    0.10
     camere
    0.10
     cottages
    0.09
     villas
    0.09
     beds
    0.09
     oversized
    0.09
     linens
    0.09
    Act Density 0.039%

    No Known Activations