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

    Neuronpedia

    INDEX
    Explanations

    phrases that categorize or describe types of things or people

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

    kind of noun / sort of noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.44
    хьтан
    -0.44
    toHaveBeenCalled
    -0.40
    httphttps
    -0.40
    ьажоргаш
    -0.39
    wait
    -0.33
     vä
    -0.32
     مست
    -0.32
     Censo
    -0.31
     sumpay
    -0.30
    POSITIVE LOGITS
    twimg
    0.60
     queſta
    0.59
     AssemblyCompany
    0.57
     Мексичка
    0.56
    flashdata
    0.55
    openzeppelin
    0.55
    mappedBy
    0.54
    VersionUID
    0.53
     típico
    0.52
    MLLoader
    0.51
    Act Density 0.013%

    No Known Activations