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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on the “1_0” (and especially the “0”) version‐number pattern in license filenames like “LICENSE_1_0.txt.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (metric
    -0.07
    dog
    -0.07
     cages
    -0.07
    Dog
    -0.06
    914
    -0.06
    Importer
    -0.06
     ******************************************************************************/↵
    -0.06
     ní
    -0.06
    .getService
    -0.06
    ement
    -0.06
    POSITIVE LOGITS
    如此
    0.07
     совет
    0.06
     evacuated
    0.06
     LUA
    0.06
    ρωση
    0.06
     Blackhawks
    0.06
     preach
    0.06
     sweater
    0.06
     فق
    0.06
     DataAccess
    0.06
    Act Density 0.001%

    No Known Activations