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

    Neuronpedia

    INDEX
    Explanations

    references to groups of people or entities, particularly in social or institutional contexts

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

    Plural nouns

    np_acts-logits-general · gemini-2.0-flash

    entities followed by possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.67
    ImageContext
    -0.63
     للاسماء
    -0.61
     réfugiés
    -0.59
     varandra
    -0.58
     frågan
    -0.56
    InitVars
    -0.54
    tagHelperRunner
    -0.54
     året
    -0.54
    uminense
    -0.52
    POSITIVE LOGITS
     own
    1.20
     ability
    1.11
     entire
    1.10
     biggest
    1.07
     favorite
    1.05
     main
    1.03
     newest
    1.02
     presence
    0.99
     original
    0.97
     largest
    0.96
    Act Density 0.280%

    No Known Activations