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

    Neuronpedia

    INDEX
    Explanations

    Image captions

    np_max-act · gemini-2.0-flash

    The neuron activates strongly on named-entity tokens—that is, proper names of people, places, and organizations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     released
    -0.07
    Those
    -0.07
    ceptors
    -0.07
     Pandora
    -0.07
     cũng
    -0.07
     Astr
    -0.07
    @test
    -0.06
    longitude
    -0.06
     Digital
    -0.06
     Transportation
    -0.06
    POSITIVE LOGITS
     coroutine
    0.06
    侧
    0.06
    _IF
    0.06
    repository
    0.06
     categorie
    0.06
     projecting
    0.06
    ıb
    0.06
    .jwt
    0.06
     pollutants
    0.06
     repairs
    0.06
    Act Density 0.010%

    No Known Activations