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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    This neuron fires on the second‐person pronoun “you,” especially when it appears in direct “Who are you…?” questions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    self-referential statements or questions regarding identity.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    strcmp
    -0.06
    .'&
    -0.06
     doGet
    -0.06
    itore
    -0.06
     �
    -0.06
    .Kind
    -0.06
     +(
    -0.06
     Describe
    -0.06
    .Parser
    -0.06
    [sizeof
    -0.06
    POSITIVE LOGITS
     primera
    0.08
     Vega
    0.07
    千
    0.07
     غذ
    0.06
    -web
    0.06
    虑
    0.06
     rainbow
    0.06
     bunch
    0.06
     Mega
    0.06
     Grammy
    0.06
    Act Density 0.004%

    No Known Activations