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

    Neuronpedia

    INDEX
    Explanations

    mixing ingredients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ฤ
    -0.06
     Burst
    -0.06
     stools
    -0.06
    实在
    -0.06
     ček
    -0.06
    rası
    -0.06
    람
    -0.06
    、私
    -0.06
     harvesting
    -0.05
    .bootstrap
    -0.05
    POSITIVE LOGITS
     strokeLine
    0.07
    subtotal
    0.07
    UBLISH
    0.07
    ！↵
    0.06
     happiness
    0.06
    Elect
    0.06
     Techn
    0.06
    checkbox
    0.06
     archived
    0.06
    >Type
    0.06
    Act Density 0.025%

    No Known Activations