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

    Neuronpedia

    INDEX
    Explanations

    terms related to security exploits and vulnerabilities in computer systems

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

    security vulnerabilities and fixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ModelAdmin
    -0.50
    extAlignment
    -0.46
     modelAndView
    -0.46
    fromnode
    -0.46
    GEBURTSDATUM
    -0.45
    üyada
    -0.43
    Xna
    -0.43
    GenerationType
    -0.42
    existsSync
    -0.41
    astify
    -0.41
    POSITIVE LOGITS
    OGND
    0.56
     lenker
    0.45
     AssemblyCulture
    0.43
    httphttps
    0.43
     vulnerabilities
    0.42
     nahilalakip
    0.41
     Vulnerability
    0.40
    tagHelper
    0.39
    loit
    0.39
     vulnerability
    0.39
    Act Density 0.216%

    No Known Activations