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

    Neuronpedia

    INDEX
    Explanations

    references to valuable or exceptional items, often metaphorically described as "gems."

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

    gems and classic works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.71
     noDo
    -0.61
    VIAF
    -0.54
    WriteBarrier
    -0.51
     AssemblyCompany
    -0.50
    astify
    -0.50
    ioutil
    -0.47
     ویکی‌پدیا
    -0.46
    这让
    -0.45
    VersionUID
    -0.44
    POSITIVE LOGITS
     classics
    0.65
     classic
    0.57
     gems
    0.54
    classic
    0.53
     masterpieces
    0.52
    Classic
    0.51
     nugget
    0.51
     经典
    0.51
     classiques
    0.51
     nuggets
    0.51
    Act Density 0.052%

    No Known Activations