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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "only" and its variations to indicate exclusivity or limitation

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

    limiting condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Karla
    -0.35
    mRecyclerView
    -0.34
     Karla
    -0.30
    ⟭
    -0.28
     throughout
    -0.28
     image
    -0.28
     mura
    -0.27
     sitt
    -0.27
     purpose
    -0.26
     ("
    -0.26
    POSITIVE LOGITS
     nahilalakip
    0.87
    ésultats
    0.80
    majánló
    0.79
    ロウィン
    0.78
    ſſung
    0.74
    mpagne
    0.73
    IsContent
    0.73
    ſicht
    0.72
    iſen
    0.70
    ementara
    0.70
    Act Density 0.020%

    No Known Activations