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

    Neuronpedia

    INDEX
    Explanations

    .view

    np_max-act · gemini-2.0-flash

    This neuron activates on plain references to a view object—i.e. occurrences of “view” (as in self.view or view) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    дах
    -0.06
    姉
    -0.06
     внут
    -0.06
     svensk
    -0.06
    HeaderValue
    -0.06
     Pazar
    -0.06
     loro
    -0.06
    �
    -0.06
     پرداخت
    -0.06
    러리
    -0.06
    POSITIVE LOGITS
     infinity
    0.07
    .W
    0.07
     tex
    0.07
     disclosures
    0.07
     PROVIDED
    0.06
     patri
    0.06
     �
    0.06
     violently
    0.06
    .Ph
    0.06
     protections
    0.06
    Act Density 0.002%

    No Known Activations