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

    Neuronpedia

    INDEX
    Explanations

    circuit

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the “Tenth Circuit” heading in appellate court opinions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    aných
    -0.07
    지막
    -0.06
    �
    -0.06
    :path
    -0.06
    cff
    -0.06
    گران
    -0.06
    (false
    -0.06
    ypical
    -0.06
    =tmp
    -0.06
    肯
    -0.06
    POSITIVE LOGITS
    uild
    0.07
     голос
    0.07
     Authorization
    0.07
    อากาศ
    0.06
    itu
    0.06
    Ком
    0.06
     inherently
    0.06
     Hos
    0.06
     čist
    0.06
     Assertion
    0.06
    Act Density 0.000%

    No Known Activations