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

    Neuronpedia

    INDEX
    Explanations

    rec

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (guess
    -0.07
    문
    -0.07
    ण
    -0.07
     ris
    -0.06
    互
    -0.06
     think
    -0.06
    	parser
    -0.06
     Boxes
    -0.06
    Encode
    -0.06
     команд
    -0.06
    POSITIVE LOGITS
    reo
    0.07
    LECT
    0.07
    рд
    0.06
    합
    0.06
    ardown
    0.06
    eee
    0.06
    /rc
    0.06
    弋
    0.06
    nerRadius
    0.06
     　　　　　　
    0.06
    Act Density 0.005%

    No Known Activations