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

    Neuronpedia

    INDEX
    Explanations

    concerns related to computer security and malware issues

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

    virus and compromise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Olímp
    -0.35
     fon
    -0.34
     intro
    -0.34
    jedi
    -0.31
    intro
    -0.31
    STAR
    -0.30
     Ara
    -0.29
     Weg
    -0.29
     Reproduce
    -0.29
     disco
    -0.28
    POSITIVE LOGITS
    ViewInit
    0.66
     AssemblyCompany
    0.64
    Rüyada
    0.64
    Personendaten
    0.59
    0.56
     Normdatei
    0.55
     الرياضيه
    0.55
     MessageBoxIcon
    0.54
    Geplaatst
    0.54
    #+#
    0.54
    Act Density 0.025%

    No Known Activations