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

    Neuronpedia

    INDEX
    Explanations

    you, us

    np_max-act · gemini-2.0-flash

    This neuron detects the second-person pronoun “you,” i.e. direct address to the user.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Scots
    -0.07
     base
    -0.07
    Mos
    -0.06
    blog
    -0.06
     speech
    -0.06
     support
    -0.06
    Sarah
    -0.06
     поход
    -0.06
     Ν
    -0.06
     electronic
    -0.06
    POSITIVE LOGITS
     attrib
    0.07
    еви
    0.07
    แล
    0.06
    .AllowUser
    0.06
    ='.
    0.06
    \Action
    0.06
    려
    0.06
    학년도
    0.06
    "),"
    0.06
    ファ
    0.06
    Act Density 0.017%

    No Known Activations