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

    Neuronpedia

    INDEX
    Explanations

    Informal conversations

    np_max-act · gemini-2.0-flash

    This neuron detects second-person references—especially the pronouns “you,” “your,” and related forms used to address the reader.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.06
    砂
    -0.06
     DbType
    -0.06
    这个
    -0.06
     podí
    -0.06
     身
    -0.06
    acz
    -0.06
     المخت
    -0.06
    McC
    -0.06
     チ
    -0.05
    POSITIVE LOGITS
     beg
    0.07
    _System
    0.07
    Gl
    0.07
     Telegram
    0.07
     flew
    0.07
    جار
    0.07
    appointed
    0.07
     irresistible
    0.07
     break
    0.06
     television
    0.06
    Act Density 0.001%

    No Known Activations