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

    Neuronpedia

    INDEX
    Explanations

    jurisdiction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Retail
    -0.07
     AX
    -0.07
    "`
    -0.06
    行
    -0.06
     authorize
    -0.06
     Hood
    -0.06
     AWS
    -0.06
    赋
    -0.06
    �
    -0.06
     proves
    -0.06
    POSITIVE LOGITS
    垃
    0.07
    쓴
    0.07
    حلم
    0.07
    もら
    0.07
     pp
    0.07
     çözüm
    0.07
     Gł
    0.06
    ritch
    0.06
    ቀ
    0.06
     WR
    0.06
    Act Density 0.016%

    No Known Activations