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

    Neuronpedia

    INDEX
    Explanations

    medicine

    np_max-act · gemini-2.0-flash

    metadata markers denoting the assistant’s turn in a chat-formatted transcript.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     shouting
    -0.07
    >t
    -0.07
    ۱۷
    -0.06
     selfies
    -0.06
     Raid
    -0.06
    review
    -0.06
    971
    -0.06
     linha
    -0.06
    .Xtra
    -0.06
     "";↵
    -0.06
    POSITIVE LOGITS
    ева
    0.07
    longleftrightarrow
    0.07
    μένου
    0.06
     　 　 　 　 　 　 　 　
    0.06
    templates
    0.06
     možná
    0.06
    Arizona
    0.06
     выход
    0.06
    0.06
     vox
    0.06
    Act Density 0.130%

    No Known Activations