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

    Neuronpedia

    INDEX
    Explanations

    ascending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rude
    -0.07
    -Christian
    -0.07
    問題
    -0.07
     д
    -0.06
    ি
    -0.06
    <Data
    -0.06
     blurry
    -0.06
    bject
    -0.06
     Naughty
    -0.06
     nationality
    -0.06
    POSITIVE LOGITS
     ascending
    0.08
     pardon
    0.07
     descending
    0.07
     الآ
    0.06
    >'.
    0.06
     今
    0.06
     Cosby
    0.06
    WillDisappear
    0.06
    ości
    0.06
    ">'.
    0.06
    Act Density 0.001%

    No Known Activations