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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unic
    -0.08
    𨐈
    -0.08
     Germ
    -0.07
     gimm
    -0.07
    걔
    -0.07
    [string
    -0.07
    -show
    -0.07
     slut
    -0.07
     artış
    -0.07
    animals
    -0.07
    POSITIVE LOGITS
     generators
    0.07
     purified
    0.07
    工序
    0.07
     Employees
    0.07
    最先进的
    0.07
    	def
    0.07
    Syntax
    0.07
     assures
    0.07
     subdiv
    0.06
    获得了
    0.06
    Act Density 0.000%

    No Known Activations