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

    Neuronpedia

    INDEX
    Explanations

    Article/post formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HOME
    -0.07
     copyrights
    -0.06
    College
    -0.06
     eleven
    -0.06
     PLA
    -0.06
     tốt
    -0.06
     Paran
    -0.06
     tabs
    -0.06
    ToDevice
    -0.06
    /access
    -0.06
    POSITIVE LOGITS
     sj
    0.07
    +'_
    0.07
    =("
    0.06
     вищ
    0.06
    |{↵
    0.06
    ↵
    0.06
     그의
    0.06
     Fountain
    0.06
    eriod
    0.06
     ㅇ
    0.06
    Act Density 0.133%

    No Known Activations