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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DFS
    -0.07
     crates
    -0.06
     through
    -0.06
    HTTP
    -0.06
     XML
    -0.06
    _regions
    -0.06
    Js
    -0.06
     Cly
    -0.06
    において
    -0.06
     onClose
    -0.06
    POSITIVE LOGITS
    verted
    0.07
    paired
    0.07
    writer
    0.06
    kv
    0.06
    prene
    0.06
     initData
    0.06
     Ð
    0.06
     Sergei
    0.06
    竞
    0.06
    nez
    0.06
    Act Density 0.023%

    No Known Activations