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

    Neuronpedia

    INDEX
    Explanations

    Raising issues/questions

    np_max-act · gemini-2.0-flash

    The neuron detects phrases that describe personally encountering or running into a problem.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     MySql
    -0.07
    器
    -0.06
     Rican
    -0.06
    	vertex
    -0.06
    iston
    -0.06
    .dist
    -0.06
    uzzle
    -0.06
    ショ
    -0.06
    ist
    -0.06
     postup
    -0.06
    POSITIVE LOGITS
     isLoading
    0.08
     คณะ
    0.08
    .mapbox
    0.07
    _POOL
    0.06
     моя
    0.06
    ριά
    0.06
    .')↵
    0.06
     Би
    0.06
     مي
    0.06
     اله
    0.06
    Act Density 0.033%

    No Known Activations