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

    Neuronpedia

    INDEX
    Explanations

    references to rights and individual entitlements

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

    own right

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.54
     дописавши
    -0.52
     ویکی‌پدی
    -0.51
     Allociné
    -0.50
     Meksiku
    -0.50
    PreferredItem
    -0.50
     <<<<<<<<<<<<<<
    -0.50
    Derbyniad
    -0.48
    Spoljašnje
    -0.47
    kháu
    -0.45
    POSITIVE LOGITS
     nonetheless
    0.51
     turut
    0.50
     vốn
    0.50
     lanjut
    0.44
    <bos>
    0.44
     dennoch
    0.44
    懸命
    0.43
    本身
    0.43
     respectively
    0.43
     likewise
    0.43
    Act Density 0.004%

    No Known Activations