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

    Neuronpedia

    INDEX
    Explanations

    People and commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incorporating
    -0.07
    鏡
    -0.07
    gress
    -0.06
     cafeteria
    -0.06
    isz
    -0.06
    本报
    -0.06
     goddess
    -0.06
     Ц
    -0.06
    ип
    -0.06
     Harness
    -0.06
    POSITIVE LOGITS
    Vec
    0.08
    (↵
    0.08
    擤
    0.08
    Dialog
    0.07
    (
↵
    0.07
    ViewItem
    0.07
    ☴
    0.07
    ㌓
    0.07
    .ForeColor
    0.07
     pcm
    0.07
    Act Density 0.042%

    No Known Activations