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

    Neuronpedia

    INDEX
    Explanations

    addressing someone

    np_max-act · gemini-2.0-flash

    This neuron detects second-person references—tokens like “you” and “your” that directly address the reader or user.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    乗
    -0.07
    _PREFIX
    -0.06
     elé
    -0.06
    _HINT
    -0.06
    afil
    -0.06
    tool
    -0.06
     آنچه
    -0.06
     bridal
    -0.06
     กระ
    -0.06
    یط
    -0.06
    POSITIVE LOGITS
    Ultra
    0.07
    ?"↵
    0.06
     Ultra
    0.06
     Fury
    0.06
    heit
    0.06
     Seks
    0.06
    ination
    0.06
    quo
    0.06
     Faker
    0.06
    Reply
    0.06
    Act Density 0.022%

    No Known Activations