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

    Neuronpedia

    INDEX
    Explanations

    Ninth

    np_max-act · gemini-2.0-flash

    The neuron activates on ordinal indicators in legal citations—particularly the “th” suffix and the word “Ninth” (as in “Ninth Circuit Rule”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ulence
    -0.07
     Reed
    -0.07
     AssemblyTrademark
    -0.07
     Decay
    -0.06
    ường
    -0.06
    ecta
    -0.06
    war
    -0.06
    .cuda
    -0.06
     Ac
    -0.06
    GROUND
    -0.06
    POSITIVE LOGITS
     ninth
    0.07
    Ÿ
    0.07
    قب
    0.06
    ----
    0.06
    ิทยาล
    0.06
    Practice
    0.06
     jmp
    0.06
     navigating
    0.06
     requ
    0.06
    بات
    0.06
    Act Density 0.001%

    No Known Activations