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

    Neuronpedia

    INDEX
    Explanations

    defensive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    createElement
    -0.08
     البلاد
    -0.08
     Istanbul
    -0.07
    띵
    -0.07
    _extractor
    -0.07
     منتخب
    -0.07
    European
    -0.07
    鹄
    -0.07
    Transport
    -0.07
    ULATOR
    -0.07
    POSITIVE LOGITS
    יס
    0.07
    𝘯
    0.07
     Procedures
    0.07
     פוס
    0.06
     コ
    0.06
    .Entry
    0.06
     LLC
    0.06
    FIXME
    0.06
     FILES
    0.06
    ünün
    0.06
    Act Density 0.005%

    No Known Activations