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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric measurement values (decimal numbers) that annotate quantitative results or parameter settings in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    EObject
    -0.07
    руг
    -0.06
    턴
    -0.06
    crast
    -0.06
    MATCH
    -0.06
    .gstatic
    -0.06
    우스
    -0.06
    PLEX
    -0.06
     jsonString
    -0.06
    iazza
    -0.06
    POSITIVE LOGITS
     Karel
    0.07
     mListener
    0.07
     ham
    0.07
     consegu
    0.06
    communic
    0.06
    ms
    0.06
    |=
    0.06
    )];↵
    0.06
     ]);
    0.06
     Blizzard
    0.06
    Act Density 0.075%

    No Known Activations