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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash

    The neuron is primarily responding to first‐person pronouns and self‐references (e.g. “I,” “my,” “I’m,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (that
    -0.08
    ...");↵
    -0.07
    ()">↵
    -0.07
    sitemap
    -0.06
     Executes
    -0.06
    qus
    -0.06
    $criteria
    -0.06
    TINGS
    -0.06
    QtCore
    -0.06
    .Criteria
    -0.06
    POSITIVE LOGITS
     allowable
    0.07
     upgrading
    0.06
    yna
    0.06
     EAST
    0.06
     Explosion
    0.06
     connections
    0.06
    urge
    0.06
    -package
    0.06
     Brazil
    0.06
    疫
    0.06
    Act Density 0.007%

    No Known Activations