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

    Neuronpedia

    INDEX
    Explanations

    ec

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    新京报
    -0.08
    oval
    -0.07
    pix
    -0.07
    unifu
    -0.07
    (required
    -0.06
    有必要
    -0.06
    ายน
    -0.06
     tribe
    -0.06
    ध
    -0.06
    -vesm
    -0.06
    POSITIVE LOGITS
     trong
    0.08
    视为
    0.07
     украин
    0.07
     forecasts
    0.07
    gold
    0.06
    当我
    0.06
    sworth
    0.06
    .mozilla
    0.06
     Gu
    0.06
     disput
    0.06
    Act Density 0.001%

    No Known Activations