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

    Neuronpedia

    INDEX
    Explanations

    DNS servers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    图书
    -0.08
     itu
    -0.07
    (Py
    -0.07
    Eb
    -0.07
    .th
    -0.07
     tersebut
    -0.07
     Trail
    -0.06
    ORTH
    -0.06
     plata
    -0.06
     PCB
    -0.06
    POSITIVE LOGITS
    赢得了
    0.07
     rewind
    0.07
     wal
    0.07
    妫
    0.07
    haul
    0.07
     başlat
    0.07
     Updating
    0.07
    errals
    0.07
    눠
    0.06
    뇐
    0.06
    Act Density 0.011%

    No Known Activations