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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron detects procedural rule citations, especially phrases like “Pursuant to Local Rule 47.5.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    研
    -0.07
     سنت
    -0.06
     tín
    -0.06
     дет
    -0.06
    	Player
    -0.06
     affairs
    -0.06
     stunt
    -0.06
    loor
    -0.06
     glyph
    -0.06
     pinterest
    -0.06
    POSITIVE LOGITS
    685
    0.06
     strengthens
    0.06
    ्ञ
    0.06
     Index
    0.06
    CEEDED
    0.06
     isKindOfClass
    0.06
    .Suppress
    0.06
     않
    0.06
    setContent
    0.06
    eenth
    0.06
    Act Density 0.002%

    No Known Activations