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

    Neuronpedia

    INDEX
    Explanations

    panel

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on the word “panel” in the boilerplate phrase “The panel unanimously concludes…” in court‐opinion texts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _REQUEST
    -0.08
    icipants
    -0.07
     Buildings
    -0.07
     Prosecutor
    -0.07
    arin
    -0.06
    Answers
    -0.06
    Restricted
    -0.06
     WPARAM
    -0.06
    urahan
    -0.06
    itect
    -0.06
    POSITIVE LOGITS
     crem
    0.07
     semi
    0.06
     podría
    0.06
    (pdf
    0.06
     multi
    0.06
    持续
    0.06
     knull
    0.06
     �
    0.06
     producción
    0.06
     ked
    0.06
    Act Density 0.000%

    No Known Activations