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

    Neuronpedia

    INDEX
    Explanations

    references to the term "bronze" in various contexts

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

    bronze door, medal, star

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.69
    makeConstraints
    -0.66
    最快更新
    -0.58
    pahan
    -0.56
     AppDelegate
    -0.56
     élector
    -0.55
    Pep
    -0.54
    extAlignment
    -0.54
    Handlung
    -0.54
    __':
    -0.54
    POSITIVE LOGITS
     Bronze
    1.10
     bronze
    1.08
    Bronze
    1.02
     BRON
    0.98
    bronze
    0.95
     Bron
    0.93
     bronce
    0.88
    Bron
    0.83
     bronzo
    0.75
     bron
    0.73
    Act Density 0.003%

    No Known Activations