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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “as” when it’s used in defining or appositive phrases (e.g. “known as,” “referred to as”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lim
    -0.07
     sah
    -0.07
     voor
    -0.07
     mascot
    -0.06
     fileType
    -0.06
     reassure
    -0.06
     het
    -0.06
     Silicone
    -0.06
    iren
    -0.06
    Calibri
    -0.06
    POSITIVE LOGITS
    [opt
    0.06
     oranı
    0.06
    거
    0.06
    .exists
    0.06
    -cols
    0.06
    과정
    0.06
     retain
    0.06
    _Customer
    0.06
     indentation
    0.06
     Archie
    0.06
    Act Density 0.060%

    No Known Activations