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

    Neuronpedia

    INDEX
    Explanations

    DAO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hook
    -0.07
     marrying
    -0.07
     hiç
    -0.06
     wel
    -0.06
     PERMISSION
    -0.06
    (names
    -0.06
     TX
    -0.06
     conc
    -0.06
    528
    -0.06
     Civ
    -0.06
    POSITIVE LOGITS
     godt
    0.07
     Tacoma
    0.06
    ＝＝
    0.06
          ↵
    0.06
    ¨¨
    0.06
     ид
    0.06
    .Flush
    0.06
    .Resolve
    0.06
     fatigue
    0.06
     теж
    0.06
    Act Density 0.000%

    No Known Activations