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
     Least
    -0.07
     Highlight
    -0.06
     کشور
    -0.06
    主人
    -0.06
    "io
    -0.06
     بعدی
    -0.06
    疗
    -0.06
    serde
    -0.06
     XIV
    -0.06
    ArrayList
    -0.06
    POSITIVE LOGITS
    accuracy
    0.07
    .Standard
    0.07
    cab
    0.06
    (page
    0.06
    �
    0.06
     Chester
    0.06
     ґ
    0.06
     Mercedes
    0.06
     printers
    0.06
    -cor
    0.06
    Act Density 0.002%

    No Known Activations