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

    Neuronpedia

    INDEX
    Explanations

    specific nouns related to various subjects, including art, biology, and technology

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

    Word before "of" and followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    professions, entities, or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.96
    enderror
    -0.85
    expandindo
    -0.83
     مشين
    -0.83
    })*/
    -0.80
     referrerpolicy
    -0.79
     defaultstate
    -0.79
     utafitiHapana
    -0.78
     referenties
    -0.78
    matchCondition
    -0.78
    POSITIVE LOGITS
     onPage
    0.45
    posedge
    0.43
    ยนต์
    0.43
    Thời
    0.42
    ambiguation
    0.41
    حدى
    0.41
    aide
    0.40
     lorem
    0.40
    iddhar
    0.40
     Fußballspieler
    0.38
    Act Density 0.650%

    No Known Activations