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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating names, locations, or unique identifiers

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

    end, United States, officials, team, Ludum, 6, Junkers', you’ve, wmd, insurance, one, kids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.56
    ppuden
    -0.51
     kasarigan
    -0.50
    ScopeManager
    -0.49
     McKnight
    -0.48
    yeth
    -0.48
    ValueGenerated
    -0.48
    yelitis
    -0.47
     protoimpl
    -0.45
    тьяна
    -0.45
    POSITIVE LOGITS
     Wikimedijinoj
    0.49
    ConstraintMaker
    0.45
    enderror
    0.40
     ब्रेकडाउन
    0.38
     Wiktionnaire
    0.38
    LikeLike
    0.35
    #+#
    0.34
     informée
    0.34
     
    0.32
     gynhyrchwyd
    0.32
    Act Density 0.069%

    No Known Activations