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

    Neuronpedia

    INDEX
    Explanations

    housing

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the term “housing” (and close variants) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     *));↵
    -0.07
     drill
    -0.07
    ki
    -0.07
    ">//
    -0.07
    bert
    -0.06
     Grande
    -0.06
    太
    -0.06
     ultra
    -0.06
    .note
    -0.06
     millionaire
    -0.06
    POSITIVE LOGITS
     housing
    0.11
     Housing
    0.10
     housed
    0.08
    ח
    0.08
     in
    0.08
    容
    0.07
    (Of
    0.07
    0.07
     wives
    0.07
    	bus
    0.07
    Act Density 0.006%

    No Known Activations