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

    Neuronpedia

    INDEX
    Explanations

    blog posts and questions

    np_max-act · gemini-2.0-flash

    Tokens that mark the assistant's turn/start of an assistant response (assistant-turn boundary).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     jika
    -0.08
     slicing
    -0.08
    ◪
    -0.08
    =?",
    -0.07
    \Blueprint
    -0.07
     uncovered
    -0.07
    عزل
    -0.07
     QTableWidgetItem
    -0.07
    จอง
    -0.07
     araştırma
    -0.07
    POSITIVE LOGITS
    입
    0.07
     AUT
    0.07
    /tos
    0.07
     kwargs
    0.07
     accum
    0.07
     appar
    0.07
     ROW
    0.06
     linewidth
    0.06
    IBUT
    0.06
    .Random
    0.06
    Act Density 0.286%

    No Known Activations