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

    Neuronpedia

    INDEX
    Explanations

    references to family members and relationships

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

    Code, usernames, or start of turn

    np_acts-logits-general · gemini-2.0-flash

    to the / user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.66
    WriteTagHelper
    -0.65
     CanadaChoose
    -0.62
    الحياه
    -0.61
    المشاركات
    -0.60
     становника
    -0.60
     الحره
    -0.56
    dflare
    -0.53
    eara
    -0.52
     فريبيس
    -0.51
    POSITIVE LOGITS
    invokeLater
    0.38
     hadapan
    0.34
     zijne
    0.33
     cunos
    0.30
     celebración
    0.29
     leeftijd
    0.29
     conhecida
    0.29
     kekasih
    0.29
     Sosten
    0.28
     vermeld
    0.28
    Act Density 0.049%

    No Known Activations