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

    Neuronpedia

    INDEX
    Explanations

    court filings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    کور
    -0.06
     bey
    -0.06
    ())↵↵
    -0.06
    _elem
    -0.06
    coop
    -0.06
     Tài
    -0.06
     Clarke
    -0.06
    OTOR
    -0.06
    -0.06
    forder
    -0.06
    POSITIVE LOGITS
     Herb
    0.06
    unsupported
    0.06
    plementary
    0.06
    �合
    0.06
     الأف
    0.06
     інозем
    0.06
     informational
    0.06
    .remaining
    0.06
    lemen
    0.06
    _TM
    0.06
    Act Density 0.009%

    No Known Activations