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

    Neuronpedia

    INDEX
    Explanations

    groups or entities

    np_max-act · gemini-2.0-flash

    This neuron is particularly sensitive to mentions of organizations or institutional entities (e.g. “group,” “media,” “venue,” “magazine,” “firm”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .button
    -0.07
     illustration
    -0.07
     owe
    -0.06
     bureauc
    -0.06
    Container
    -0.06
    ussed
    -0.06
     Near
    -0.06
     furthermore
    -0.06
     originals
    -0.06
    .CompareTag
    -0.06
    POSITIVE LOGITS
    هاي
    0.07
    bairro
    0.07
     setC
    0.06
     []
↵
    0.06
     ",↵
    0.06
     сайті
    0.06
    perPage
    0.06
     ober
    0.06
    pais
    0.06
    CUSTOM
    0.06
    Act Density 0.111%

    No Known Activations