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

    Neuronpedia

    INDEX
    Explanations

    fiction plots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    拜
    -0.06
     autocomplete
    -0.06
     Nhất
    -0.06
    .cent
    -0.06
     Ц
    -0.06
     Bid
    -0.06
     reelection
    -0.06
     берез
    -0.06
    =Y
    -0.06
    енную
    -0.06
    POSITIVE LOGITS
    联盟
    0.07
     nær
    0.07
     hiçbir
    0.07
    oneksi
    0.07
     الهند
    0.06
     döneminde
    0.06
     initiating
    0.06
    ptions
    0.06
     predicting
    0.06
     vigorous
    0.06
    Act Density 0.042%

    No Known Activations