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

    Neuronpedia

    INDEX
    Explanations

    ring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     memorandum
    -0.08
    /she
    -0.07
     Advertisement
    -0.06
     φορ
    -0.06
    779
    -0.06
     Putin
    -0.06
    ﻴ
    -0.06
    akeup
    -0.06
    ζ
    -0.06
    	where
    -0.06
    POSITIVE LOGITS
    .GetSize
    0.08
    .Native
    0.07
     King
    0.07
    larım
    0.07
    ledik
    0.06
    bomb
    0.06
    \modules
    0.06
    ?</
    0.06
    갔다
    0.06
     řadu
    0.06
    Act Density 0.003%

    No Known Activations