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

    Neuronpedia

    INDEX
    Explanations

    bracket symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cop
    -0.07
     aba
    -0.07
     Num
    -0.07
     Helena
    -0.07
     Prevent
    -0.07
     DP
    -0.07
    dds
    -0.07
     sauna
    -0.07
    efon
    -0.07
    败
    -0.07
    POSITIVE LOGITS
     fabrics
    0.07
    [${
    0.07
    过来
    0.06
    Stub
    0.06
    _BASE
    0.06
    (indexPath
    0.06
     LIVE
    0.06
    [id
    0.06
     　　　　　　　　　
    0.06
     jejím
    0.06
    Act Density 0.001%

    No Known Activations