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

    Neuronpedia

    INDEX
    Explanations

    Hacking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     दूध
    -0.09
     religi
    -0.09
     ингреди
    -0.09
     reaks
    -0.09
     Messi
    -0.08
     Churches
    -0.08
     religión
    -0.08
     धार्मिक
    -0.08
     décès
    -0.08
    Bedrooms
    -0.08
    POSITIVE LOGITS
     hacker
    0.18
     cybers
    0.18
     hackers
    0.17
     cyber
    0.17
     cybersecurity
    0.17
     malware
    0.16
     hacking
    0.16
    Cyber
    0.15
     ransomware
    0.14
     phishing
    0.14
    Act Density 0.053%

    No Known Activations