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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     $_
    -0.08
    手机版
    -0.07
    _news
    -0.07
    답
    -0.07
     Drone
    -0.06
    엨
    -0.06
     Blanc
    -0.06
     Guid
    -0.06
     NS
    -0.06
    mod
    -0.06
    POSITIVE LOGITS
     характер
    0.09
     görü
    0.08
     откр
    0.08
     actors
    0.08
    منذ
    0.07
    كا
    0.07
     наблюда
    0.07
    .Valid
    0.07
    病理
    0.07
     PCR
    0.07
    Act Density 0.001%

    No Known Activations