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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash

    This neuron detects named entities—proper nouns such as people’s names, organizations, places, titles, and similar capitalized terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    차
    -0.06
     towing
    -0.06
    Owner
    -0.06
     blatant
    -0.06
    _pri
    -0.06
     additional
    -0.06
     vortex
    -0.06
     rencont
    -0.06
    érieur
    -0.06
    _lower
    -0.06
    POSITIVE LOGITS
    ocop
    0.07
    ]+)/
    0.07
     storyboard
    0.06
    clusion
    0.06
    `${
    0.06
     너무
    0.06
    SES
    0.06
    olders
    0.06
    '])
↵
    0.06
    ])/
    0.06
    Act Density 0.069%

    No Known Activations