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

    Neuronpedia

    INDEX
    Explanations

    Personal narratives/conversations

    np_max-act · gemini-2.0-flash

    Instances of dialogue attribution — words naming the speaker or speech verbs (e.g., "sergeant", "replied", "answered", "said") indicating reported speech.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    .↵↵
    -0.07
    ?↵↵
    -0.07
    ぇ
    -0.06
    !',↵
    -0.06
     shed
    -0.06
    lings
    -0.06
     HomeController
    -0.06
     Marc
    -0.06
    removeAttr
    -0.06
    entication
    -0.06
    POSITIVE LOGITS
    سام
    0.07
     деревян
    0.07
     hurricanes
    0.06
     науки
    0.06
     Sym
    0.06
    粉
    0.06
     كامل
    0.06
    ellery
    0.06
    šku
    0.06
    &,
    0.06
    Act Density 0.091%

    No Known Activations