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

    Neuronpedia

    INDEX
    Explanations

    Customer reviews over time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =row
    -0.07
     생활
    -0.07
     barcelona
    -0.07
     운영
    -0.07
    国家
    -0.07
    才
    -0.06
    utschen
    -0.06
    .SetInt
    -0.06
    giatan
    -0.06
    Türkiye
    -0.06
    POSITIVE LOGITS
    何
    0.07
     Комп
    0.06
     agent
    0.06
    528
    0.06
    /em
    0.06
     pai
    0.06
     bloss
    0.06
    ๊
    0.06
    -П
    0.06
    orph
    0.06
    Act Density 0.016%

    No Known Activations