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

    Neuronpedia

    INDEX
    Explanations

    physics equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gratuits
    -0.07
     miło
    -0.07
    	NdrFc
    -0.07
     Dragon
    -0.07
     Isa
    -0.07
     uncon
    -0.07
     Green
    -0.06
     malt
    -0.06
     rabbit
    -0.06
     tribes
    -0.06
    POSITIVE LOGITS
     Petite
    0.08
    	points
    0.07
    面向
    0.07
    ctrine
    0.07
    こちら
    0.07
    UREMENT
    0.07
    各个方面
    0.07
    ometers
    0.07
    _FORCE
    0.07
    ም
    0.07
    Act Density 0.014%

    No Known Activations