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

    Neuronpedia

    INDEX
    Explanations

    specific biological or physiological processes and their components

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

    Word after articles ("a", "an", "the")

    np_acts-logits-general · gemini-2.0-flash

    articles followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pri
    -0.30
     quality
    -0.28
     Level
    -0.26
     monter
    -0.26
     and
    -0.26
    ,
    -0.25
     compare
    -0.25
     level
    -0.25
     “
    -0.24
     recon
    -0.24
    POSITIVE LOGITS
     المعيارى
    0.84
     Dieſe
    0.74
    <unused47>
    0.73
     ویکی‌پدی
    0.73
    <unused16>
    0.73
    <unused3>
    0.73
    <unused23>
    0.73
    <unused41>
    0.73
    <unused14>
    0.73
    <unused8>
    0.73
    Act Density 0.411%

    No Known Activations