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

    Neuronpedia

    INDEX
    Explanations

    awards

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of awards and their recipients (award-related announcement language).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ımlı
    -0.07
     út
    -0.06
     greedy
    -0.06
    Putin
    -0.06
     colonial
    -0.06
    ceeded
    -0.06
     Mein
    -0.06
    україн
    -0.06
    ..."↵↵
    -0.06
     Bluetooth
    -0.06
    POSITIVE LOGITS
    thetic
    0.07
    σχ
    0.07
    veled
    0.06
     hải
    0.06
    ΑΓ
    0.06
    CustomAttributes
    0.06
    ethical
    0.06
    \Storage
    0.06
    ableView
    0.06
    marshaller
    0.06
    Act Density 0.018%

    No Known Activations