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

    Neuronpedia

    INDEX
    Explanations

    held

    np_max-act · gemini-2.0-flash

    information related to athletic competitions and events.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects phrasing that describes when and where an event took place—specifically the “was held on” date/location construction.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    เหน
    -0.06
    disk
    -0.06
     fails
    -0.06
     dor
    -0.06
     Pří
    -0.06
    ﾍ
    -0.06
    ivable
    -0.06
     tex
    -0.06
    906
    -0.06
    Alive
    -0.06
    POSITIVE LOGITS
    ************************
    0.08
    .showError
    0.07
     وكان
    0.06
    _fmt
    0.06
    "↵↵↵
    0.06
    Quaternion
    0.06
    !?
    0.06
    CompanyName
    0.06
    seg
    0.06
    .fetchall
    0.06
    Act Density 0.007%

    No Known Activations