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

    Neuronpedia

    INDEX
    Explanations

    wage (war)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Instead
    -0.08
    	echo
    -0.07
     velocities
    -0.06
     encode
    -0.06
     blocked
    -0.06
     juni
    -0.06
     filt
    -0.06
     mistakes
    -0.06
     Rotation
    -0.06
    不足
    -0.06
    POSITIVE LOGITS
     waged
    0.19
     Wage
    0.09
     wage
    0.08
    år
    0.07
     идет
    0.07
     strugg
    0.07
     дина
    0.07
    (dateTime
    0.06
     dedicated
    0.06
    เกษตร
    0.06
    Act Density 0.003%

    No Known Activations