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

    Neuronpedia

    INDEX
    Explanations

    granite

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of high-end kitchen or home finish materials (e.g., granite, tile, custom cabinetry).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     intestinal
    -0.07
    population
    -0.07
     Mädchen
    -0.07
    PFN
    -0.07
     مان
    -0.07
    _OPEN
    -0.06
    branch
    -0.06
    _zoom
    -0.06
    _FILTER
    -0.06
     Ven
    -0.06
    POSITIVE LOGITS
     Granite
    0.08
    isko
    0.07
    hoo
    0.06
    )'),
    0.06
    developer
    0.06
    UINT
    0.06
    Rock
    0.06
    ollah
    0.06
    ัวหน
    0.06
     setName
    0.06
    Act Density 0.003%

    No Known Activations