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

    Neuronpedia

    INDEX
    Explanations

    security vulnerabilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reunion
    -0.09
    	glm
    -0.09
     partidos
    -0.08
    .scalar
    -0.08
     yards
    -0.08
    Crud
    -0.08
     вку
    -0.08
     房
    -0.08
    ा�
    -0.08
     Amenities
    -0.08
    POSITIVE LOGITS
     malware
    0.18
     phishing
    0.17
     ransomware
    0.16
    漏洞
    0.16
     malicious
    0.16
     spyware
    0.14
     Malware
    0.14
     vulnerabilities
    0.14
     vulnerability
    0.14
     vuln
    0.14
    Act Density 0.042%

    No Known Activations