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

    Neuronpedia

    INDEX
    Explanations

    Repeated/generic text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Derived
    -0.07
     والن
    -0.06
     cron
    -0.06
     boxer
    -0.06
    mount
    -0.06
    페이지
    -0.06
    wei
    -0.06
     Wei
    -0.06
     boxing
    -0.06
    เพล
    -0.06
    POSITIVE LOGITS
     عنوان
    0.07
     FileType
    0.06
     stalk
    0.06
    ạt
    0.06
     vulnerabilities
    0.06
     siden
    0.06
     <
    0.06
     tags
    0.06
    William
    0.06
     totaled
    0.06
    Act Density 0.005%

    No Known Activations