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

    Neuronpedia

    INDEX
    Explanations

    names and familial connections within a narrative

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

    surnames and relationship status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.81
    setVerticalGroup
    -0.64
     kaarangay
    -0.63
     snippetHide
    -0.63
    AddTagHelper
    -0.61
     للاسماء
    -0.61
    bootstrapcdn
    -0.59
    WriteTagHelper
    -0.58
    MigrationBuilder
    -0.55
     transfieras
    -0.52
    POSITIVE LOGITS
     married
    0.77
    married
    0.68
     fiancé
    0.66
     fiancée
    0.62
     fiance
    0.60
     girlfriend
    0.60
     Married
    0.56
     unmarried
    0.55
     wife
    0.52
     boyfriend
    0.52
    Act Density 0.001%

    No Known Activations