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

    Neuronpedia

    INDEX
    Explanations

    argumentative writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    ・・・・
    -0.07
     THERE
    -0.07
     Gambling
    -0.07
     제
    -0.07
    Rooms
    -0.07
     compl
    -0.07
    管制
    -0.07
     continue
    -0.07
     수도
    -0.07
    POSITIVE LOGITS
     rửa
    0.07
    .getUrl
    0.07
    szed
    0.07
     remix
    0.07
     Bü
    0.07
     Hamburg
    0.07
    chner
    0.07
    .cuda
    0.07
    爔
    0.07
    鏊
    0.06
    Act Density 0.136%

    No Known Activations