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

    Neuronpedia

    INDEX
    Explanations

    configuration or markdown list item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amended
    0.37
     dumps
    0.37
     accelerometer
    0.36
     ArrayList
    0.36
     seus
    0.36
     FDIC
    0.36
    ут
    0.36
     USAID
    0.35
     asli
    0.35
     Runs
    0.35
    POSITIVE LOGITS
    首歌
    0.44
    Brock
    0.44
    starting
    0.41
    Philip
    0.41
     ظ
    0.40
    就行
    0.38
    Topbar
    0.38
     frameborder
    0.38
    创建一个
    0.37
    localStorage
    0.36
    Act Density 0.000%

    No Known Activations