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

    Neuronpedia

    INDEX
    Explanations

    wills and bequests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xFFFFFFFF
    -0.07
     instability
    -0.06
    对方
    -0.06
     πολι
    -0.06
     สำน
    -0.06
     bcm
    -0.06
     hâlâ
    -0.06
     dicks
    -0.06
     shitty
    -0.06
     đúng
    -0.06
    POSITIVE LOGITS
    	glm
    0.07
     uncovered
    0.07
     Revelation
    0.07
     complained
    0.06
    QE
    0.06
    .A
    0.06
     Allen
    0.06
    Slinky
    0.06
     renters
    0.06
     DOE
    0.06
    Act Density 0.007%

    No Known Activations