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

    Neuronpedia

    INDEX
    Explanations

    references to formal titles or addresses in a dialogue context

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

    legal quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Derbyniad
    -0.45
     ProtoMessage
    -0.44
    neſs
    -0.43
    Diweddarwch
    -0.40
     ſche
    -0.38
    UnitTesting
    -0.38
     ámbitos
    -0.38
     cauſe
    -0.37
    ntlet
    -0.36
    IsContent
    -0.36
    POSITIVE LOGITS
     numerus
    0.52
    AsUp
    0.46
    Statistiche
    0.41
     Weich
    0.41
    AndEndTag
    0.40
    richTextPanel
    0.40
     Has
    0.40
     Caballero
    0.39
    üglich
    0.39
     فريبيس
    0.39
    Act Density 0.018%

    No Known Activations