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

    Neuronpedia

    INDEX
    Explanations

    modern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     şark
    -0.07
    ández
    -0.07
     무엇
    -0.07
    银行
    -0.07
     stabbing
    -0.07
     Elliott
    -0.07
    aub
    -0.06
     첨부파일
    -0.06
    _ratings
    -0.06
     guilt
    -0.06
    POSITIVE LOGITS
     modern
    0.17
    Modern
    0.14
     Modern
    0.14
    modern
    0.10
     Mirror
    0.07
     moderne
    0.07
    [maxn
    0.07
    21
    0.07
     moden
    0.07
     contempor
    0.06
    Act Density 0.012%

    No Known Activations