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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    戏
    -0.06
    ifiers
    -0.06
     jewels
    -0.06
     flor
    -0.06
    uilt
    -0.06
     CNS
    -0.06
    -users
    -0.06
     awk
    -0.06
    <=(
    -0.06
     AIDS
    -0.06
    POSITIVE LOGITS
     cameras
    0.06
    //}↵
    0.06
    漢
    0.06
     BrowserRouter
    0.06
     marriages
    0.06
     справж
    0.06
     Dropbox
    0.06
     효과
    0.06
     Tradable
    0.06
    _popup
    0.06
    Act Density 0.058%

    No Known Activations