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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    无人驾驶
    -0.08
     plot
    -0.08
    "title
    -0.07
     Revenue
    -0.07
    nych
    -0.07
    .yaml
    -0.07
    idos
    -0.06
    -ms
    -0.06
    仲裁
    -0.06
    وط
    -0.06
    POSITIVE LOGITS
    Tri
    0.07
     Tri
    0.07
     Глав
    0.07
    xFC
    0.06
     Notre
    0.06
    岘
    0.06
    Legend
    0.06
    amedi
    0.06
    -angle
    0.06
    뚫
    0.06
    Act Density 0.013%

    No Known Activations