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

    Neuronpedia

    INDEX
    Explanations

    distance calculations

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    .presentation
    -0.07
    Reporting
    -0.07
    ragments
    -0.07
     vulnerabilities
    -0.07
     certifications
    -0.06
    기술
    -0.06
     SCM
    -0.06
    .review
    -0.06
    Saturday
    -0.06
    _reference
    -0.06
    POSITIVE LOGITS
     insecure
    0.07
     sched
    0.07
     друг
    0.07
    ++;
↵
↵
    0.07
    将会
    0.07
    cpp
    0.07
    
↵

↵
    0.07
    \\\
    0.06
     имя
    0.06
    宴
    0.06
    Act Density 0.028%

    No Known Activations