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

    Neuronpedia

    INDEX
    Explanations

    first-person personal pronouns and references to the speaker's experiences

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

    first-person statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forstå
    -0.32
     débats
    -0.32
     Stone
    -0.31
     content
    -0.30
     legitimate
    -0.30
     enfans
    -0.29
     Función
    -0.29
     contenido
    -0.28
     pensées
    -0.28
     ouvrages
    -0.28
    POSITIVE LOGITS
    MigrationBuilder
    0.81
    SequentialGroup
    0.80
    delwed
    0.72
     <>",
    0.72
     Meksiku
    0.71
     հղումներ
    0.69
    IntoConstraints
    0.68
    EndContext
    0.68
    IsMutable
    0.68
     الرياضيه
    0.67
    Act Density 0.033%

    No Known Activations