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

    Neuronpedia

    INDEX
    Explanations

    possessive nouns and terms for groups of people.

    oai_token-act-pair · gemini-2.0-flash

    apostrophes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    </thead>
    -0.52
    ⓘ
    -0.50
     prayed
    -0.47
     volont
    -0.47
     transmiti
    -0.45
    ദ്
    -0.45
     doubted
    -0.45
     Critics
    -0.45
     unfolding
    -0.44
     fawn
    -0.44
    POSITIVE LOGITS
     HasFactory
    0.79
     autorytatywna
    0.76
    FunctionFlags
    0.72
     चीज़ों
    0.69
    {}/
    0.67
    webElementXpaths
    0.67
    AsUp
    0.65
    хьтан
    0.65
    Autoritní
    0.65
    BoxShadow
    0.65
    Act Density 2.601%

    No Known Activations