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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conced
    -0.07
    دين
    -0.07
    .GetCurrentMethod
    -0.07
    adians
    -0.07
    高血压
    -0.07
     dém
    -0.07
    �
    -0.07
    认真
    -0.07
    ervations
    -0.06
    新人玩家
    -0.06
    POSITIVE LOGITS
     donde
    0.07
    (Size
    0.07
     Emma
    0.07
    roomId
    0.06
     הבי
    0.06
    פג
    0.06
    (arc
    0.06
     escape
    0.06
    实现了
    0.06
     '~/
    0.06
    Act Density 0.000%

    No Known Activations