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

    Neuronpedia

    INDEX
    Explanations

    County

    np_max-act · gemini-2.0-flash

    The neuron is detecting mentions of U.S. counties (proper‐name + “County”) within the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    运
    -0.06
     وت
    -0.06
    UIImage
    -0.06
    stringValue
    -0.06
     lineWidth
    -0.06
    .prepend
    -0.06
    _directory
    -0.06
    รค
    -0.06
    	FROM
    -0.06
    <(),
    -0.06
    POSITIVE LOGITS
     screws
    0.07
     Chow
    0.07
     realization
    0.07
    ον
    0.06
     exhaust
    0.06
    ONT
    0.06
    hin
    0.06
     weighted
    0.06
     ranged
    0.06
    ่อง
    0.06
    Act Density 0.122%

    No Known Activations