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

    Neuronpedia

    INDEX
    Explanations

    we/our/ourselves

    np_max-act · gemini-2.0-flash

    The neuron responds to uses of the first-person plural, i.e. instances of “we,” “our,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    cdf
    -0.08
    ama
    -0.07
     tensors
    -0.07
    _revision
    -0.07
     OSP
    -0.07
    (bar
    -0.07
    fast
    -0.06
     Mama
    -0.06
     προϊ
    -0.06
     Slam
    -0.06
    POSITIVE LOGITS
    :]↵↵
    0.06
    ])),↵
    0.06
    dataTable
    0.06
    ZO
    0.06
    �
    0.06
    북
    0.06
    .");
↵
    0.06
     Tr
    0.06
     didSet
    0.06
    ким
    0.06
    Act Density 0.058%

    No Known Activations