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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or person-specific language

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

    person and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.65
    arangay
    -0.54
    Tikang
    -0.52
     navide
    -0.52
     referenties
    -0.52
     dė
    -0.51
     surla
    -0.51
    Географиясе
    -0.51
     chwil
    -0.50
     ProtoMessage
    -0.50
    POSITIVE LOGITS
     person
    0.77
     Person
    0.69
     man
    0.65
    Person
    0.64
     woman
    0.64
     людини
    0.60
     persons
    0.60
     человек
    0.59
     человека
    0.59
    Persons
    0.57
    Act Density 0.017%

    No Known Activations