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

    Neuronpedia

    INDEX
    Explanations

    truncated text

    np_max-act · gemini-2.0-flash

    markers of web/transcript formatting and navigation, including timestamps, section headers, boilerplate notices, and prompts to expand truncated content.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    .alt
    -0.07
     touchscreen
    -0.07
     spectacle
    -0.07
     Mediterranean
    -0.07
     grenade
    -0.07
     jej
    -0.06
     spectro
    -0.06
    专科
    -0.06
    .AddTransient
    -0.06
     verses
    -0.06
    POSITIVE LOGITS
    手中
    0.07
     Giving
    0.07
     EA
    0.07
    lius
    0.07
    دير
    0.07
     beliefs
    0.06
    社會
    0.06
     outlined
    0.06
    xiety
    0.06
    心境
    0.06
    Act Density 0.022%

    No Known Activations