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

    Neuronpedia

    INDEX
    Explanations

    radial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     salary
    -0.07
    য়া
    -0.07
     remed
    -0.07
     Assuming
    -0.07
     Dean
    -0.07
     rémun
    -0.07
    هر
    -0.07
     Salary
    -0.07
     jest
    -0.07
     جعل
    -0.06
    POSITIVE LOGITS
     rays
    0.09
     larga
    0.09
     combating
    0.09
     combatir
    0.09
    еспондент
    0.08
    etric
    0.08
    荣耀
    0.08
    ന്നു
    0.08
    ทะ
    0.08
     centrifugal
    0.08
    Act Density 0.014%

    No Known Activations