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

    Neuronpedia

    INDEX
    Explanations

    references to the Canon of judicial conduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Canon 5

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <h2>
    -0.43
     United
    -0.38
     Eddy
    -0.37
    s
    -0.37
    ↵↵↵↵
    -0.37
     ups
    -0.36
    islative
    -0.35
    Ti
    -0.35
     Psi
    -0.35
    ための
    -0.35
    POSITIVE LOGITS
    Canon
    2.22
     Canon
    2.20
     canon
    1.91
    canon
    1.80
     canons
    1.30
     Canonical
    1.02
    Canonical
    0.97
     canonical
    0.93
     cannon
    0.87
    canonical
    0.82
    Act Density 0.006%

    No Known Activations