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

    Neuronpedia

    INDEX
    Explanations

    symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xm
    -0.06
    !")↵
    -0.06
     disregard
    -0.06
     Calculation
    -0.06
     pur
    -0.06
     operating
    -0.06
     shaking
    -0.06
     Ecuador
    -0.06
    "'↵
    -0.06
     Clean
    -0.06
    POSITIVE LOGITS
     giá
    0.07
    .shell
    0.07
    나요
    0.07
    :;"
    0.07
     symbolic
    0.06
    *y
    0.06
    /auto
    0.06
    ivos
    0.06
    023
    0.06
    .RowIndex
    0.06
    Act Density 0.017%

    No Known Activations