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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash

    The neuron activates on the floating-point version numbers in code license headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ÓN
    -0.07
    造
    -0.06
    태
    -0.06
    ón
    -0.06
     nors
    -0.06
    >).
    -0.06
    cih
    -0.06
    wcs
    -0.06
     dzieci
    -0.06
    rdf
    -0.06
    POSITIVE LOGITS
     Fantastic
    0.07
     timetable
    0.07
    Job
    0.06
     disk
    0.06
     tabs
    0.06
    记录
    0.06
    灭
    0.06
     прояв
    0.06
    535
    0.06
     graceful
    0.06
    Act Density 0.002%

    No Known Activations