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

    Neuronpedia

    INDEX
    Explanations

    cost in dollars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     orn
    -0.09
     Tween
    -0.09
     дроб
    -0.09
     Mathf
    -0.08
     inú
    -0.08
     используется
    -0.08
     numpy
    -0.08
     Adjustment
    -0.08
     Tibetan
    -0.08
     Taschen
    -0.08
    POSITIVE LOGITS
     cybersecurity
    0.15
     ransomware
    0.15
     cyber
    0.13
     vulnerabilities
    0.12
     phishing
    0.11
    Cyber
    0.11
     encrypted
    0.11
     confidentiality
    0.11
     Cyber
    0.11
     ransom
    0.10
    Act Density 0.048%

    No Known Activations