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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating rarity or unusual occurrences

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

    "rare" or words indicating rarity

    np_acts-logits-general · gemini-2.0-flash

    rare or uncommon concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ingham
    -0.54
    клопе
    -0.51
    ilirsiniz
    -0.50
     Sack
    -0.46
    óri
    -0.46
     ivelany
    -0.45
    vitis
    -0.45
     newOwner
    -0.44
    getFullYear
    -0.43
     createState
    -0.43
    POSITIVE LOGITS
     rare
    3.11
     rarity
    2.85
    Rare
    2.66
     rarer
    2.63
    rare
    2.62
     Rare
    2.60
     rarest
    2.44
     RARE
    2.37
     uncommon
    2.29
     rares
    2.17
    Act Density 0.433%

    No Known Activations