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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of numbered event or conference labels—especially “E3” plus year tokens (e.g. “E3 2018,” “2017,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Movie
    -0.07
    摇
    -0.06
    cloth
    -0.06
    рог
    -0.06
    重新
    -0.06
    lech
    -0.06
    ských
    -0.06
    ()].
    -0.06
    ैग
    -0.05
    جا
    -0.05
    POSITIVE LOGITS
     -(
    0.06
     complaint
    0.06
     UE
    0.06
    nemonic
    0.06
     paddle
    0.06
    (DbContext
    0.06
    ContentLoaded
    0.06
    GetName
    0.06
    _print
    0.06
     motion
    0.06
    Act Density 0.006%

    No Known Activations