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

    Neuronpedia

    INDEX
    Explanations

    elements related to references and external links in a document

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

    external links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BagConstraints
    -0.57
     فريبيس
    -0.52
    versiti
    -0.51
    AsUp
    -0.46
    Personensuche
    -0.44
    Сыртқы
    -0.44
     محفوظة
    -0.44
     synap
    -0.43
    cipar
    -0.43
    المشاركات
    -0.43
    POSITIVE LOGITS
    了呢
    0.41
    delwed
    0.39
    StructEnd
    0.37
    SharedCtor
    0.37
     player
    0.37
     Player
    0.36
     joueur
    0.36
    illots
    0.35
    RTLU
    0.35
     jugador
    0.34
    Act Density 0.010%

    No Known Activations