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

    Neuronpedia

    INDEX
    Explanations

    title

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NONE
    -0.08
    富贵
    -0.08
     hood
    -0.07
    	Debug
    -0.07
    _device
    -0.07
    离不开
    -0.07
     get
    -0.07
    []{
    -0.07
     U
    -0.07
     Received
    -0.07
    POSITIVE LOGITS
    可以把
    0.08
    쁨
    0.08
    _BINARY
    0.08
    elps
    0.07
    Arizona
    0.07
    キッチ
    0.07
    أفكار
    0.07
    귱
    0.07
    ализ
    0.07
     البيان
    0.07
    Act Density 0.004%

    No Known Activations