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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    орон
    -0.06
     Sphinx
    -0.06
     downgrade
    -0.06
     Nun
    -0.06
     Winn
    -0.06
     hemos
    -0.06
    inx
    -0.06
    creasing
    -0.06
     некоторых
    -0.06
     leopard
    -0.06
    POSITIVE LOGITS
    STA
    0.06
     εκεί
    0.06
    (section
    0.06
     exclude
    0.06
    벤트
    0.06
     pada
    0.06
    keep
    0.06
     parking
    0.06
     GRAT
    0.06
    (asset
    0.06
    Act Density 0.120%

    No Known Activations