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

    Neuronpedia

    INDEX
    Explanations

    terms related to cybersecurity threats and vulnerabilities

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

    potential online scams or malware

    np_acts-logits-general · gemini-2.0-flash

    scam, malware, and offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    posedge
    -0.58
    BeginInit
    -0.58
    transQ
    -0.55
    ArgsConstructor
    -0.46
    rivit
    -0.45
    HasForeignKey
    -0.44
    peq
    -0.43
     Enix
    -0.42
    таратура
    -0.42
    énario
    -0.42
    POSITIVE LOGITS
     scam
    0.65
     scammed
    0.64
     hoax
    0.63
     scams
    0.62
     Bann
    0.60
     Income
    0.59
     propOrder
    0.58
     malware
    0.58
    oneofs
    0.58
     income
    0.57
    Act Density 0.221%

    No Known Activations