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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron activates on personal names (especially attorneys’, judges’, or parties’ full names, often with initials and titles) in legal case documents.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Wy
    -0.07
     인구
    -0.06
    .Login
    -0.06
    isoft
    -0.06
     contradict
    -0.06
     Kh
    -0.06
    .Power
    -0.06
    ぇ
    -0.06
     può
    -0.06
     paul
    -0.06
    POSITIVE LOGITS
     tecn
    0.07
    .ascii
    0.07
     захист
    0.06
    InnerHTML
    0.06
    pared
    0.06
    верд
    0.06
     chuyến
    0.06
    خوان
    0.06
    Internal
    0.06
     creds
    0.06
    Act Density 0.048%

    No Known Activations