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

    Neuronpedia

    INDEX
    Explanations

    terms related to cybersecurity vulnerabilities and threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Cybersecurity, hacking, vulnerabilities

    np_acts-logits-general · gemini-2.0-flash

    hacking and vulnerabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pēc
    -0.59
    autoreleasepool
    -0.59
     mxArray
    -0.58
    UnknownFieldSet
    -0.56
    ondissement
    -0.54
     Orrell
    -0.53
     BoxFit
    -0.52
     doubtnut
    -0.52
     Shreve
    -0.51
    GraphicsUnit
    -0.50
    POSITIVE LOGITS
     hacking
    1.28
     hacker
    1.27
     vulnerabilities
    1.24
     hackers
    1.23
     attack
    1.22
     attackers
    1.22
     attacks
    1.18
     cyber
    1.17
     security
    1.17
     vulnerability
    1.17
    Act Density 0.479%

    No Known Activations