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

    Neuronpedia

    INDEX
    Explanations

    linguistic structures and categories related to plurality and noun forms

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

    plural, singular, or grammatical forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.61
    Autoritní
    -0.48
     חיצוניים
    -0.48
    发表于
    -0.45
    riwal
    -0.43
    AlterField
    -0.43
    المشاركات
    -0.43
    ForTesting
    -0.42
    uxxxx
    -0.42
     Korea
    -0.42
    POSITIVE LOGITS
     plural
    0.61
     singular
    0.60
    Plural
    0.59
    Singular
    0.57
    plural
    0.56
     Plural
    0.55
     Singular
    0.54
    singular
    0.53
    Noun
    0.46
    urals
    0.46
    Act Density 0.094%

    No Known Activations