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

    Neuronpedia

    INDEX
    Explanations

    references to legal terminology and judicial procedures

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

    Numbers enclosed in square brackets

    np_acts-logits-general · gemini-2.0-flash

    notes and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     block
    -0.49
    </h2>
    -0.41
     put
    -0.41
    </h1>
    -0.40
     you
    -0.40
    แจ
    -0.40
     last
    -0.39
     set
    -0.38
    Job
    -0.38
     complex
    -0.38
    POSITIVE LOGITS
     дописавши
    1.10
     Ibid
    0.95
    تقاوى
    0.93
     ProtoMessage
    0.84
    RegressionTest
    0.83
    Ibid
    0.83
    ↩
    0.82
    脚注の使い方
    0.82
     HttpNotFound
    0.82
     ibid
    0.80
    Act Density 0.233%

    No Known Activations