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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    mentions of software or system security vulnerabilities and exploitation within cybersecurity contexts.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    idue
    -0.07
    ヴァ
    -0.07
    โต
    -0.07
     ry
    -0.06
    sexy
    -0.06
    MouseButton
    -0.06
    _TEXTURE
    -0.06
     doby
    -0.06
    _SPELL
    -0.06
     coefficient
    -0.06
    POSITIVE LOGITS
    […]
    0.06
    continent
    0.06
     thoại
    0.06
     guit
    0.06
     Accessed
    0.06
     initial
    0.06
     (...)
    0.06
    <Props
    0.06
     Brady
    0.06
     defy
    0.06
    Act Density 0.021%

    No Known Activations