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

    Neuronpedia

    INDEX
    Explanations

    almost

    np_max-act · gemini-2.0-flash

    tokens marking the assistant role or the start of an assistant response in a chat-format transcript.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    bitset
    -0.07
     날
    -0.06
    次
    -0.06
    (IN
    -0.06
    gresql
    -0.06
     жит
    -0.06
    partial
    -0.06
     grub
    -0.06
    IME
    -0.06
    날
    -0.06
    POSITIVE LOGITS
    >()->
    0.06
     Eleven
    0.06
     Northern
    0.06
     Trey
    0.06
    .mongo
    0.06
     Crushing
    0.06
    ================
    0.06
     """↵↵
    0.06
     coment
    0.06
    　　　　　　　　　　
    0.06
    Act Density 0.033%

    No Known Activations