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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    This neuron fires on personal names and other references to individual people (proper nouns).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Inspection
    -0.08
     Excellence
    -0.08
     دین
    -0.07
     affiliation
    -0.06
     Contribution
    -0.06
     درب
    -0.06
     Cou
    -0.06
    oğ
    -0.06
     싱
    -0.06
     Facility
    -0.06
    POSITIVE LOGITS
    ensored
    0.07
    Missing
    0.06
     bastante
    0.06
    jr
    0.06
     jeho
    0.06
    ivate
    0.06
    ानक
    0.06
    ertz
    0.06
    write
    0.06
    _CRC
    0.06
    Act Density 0.020%

    No Known Activations