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

    Neuronpedia

    INDEX
    Explanations

    Forgetting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rebuilding
    -0.08
    表
    -0.07
    outputs
    -0.07
    证
    -0.07
    òn
    -0.07
    	va
    -0.07
    마다
    -0.07
     \"{
    -0.07
    还要
    -0.07
    _pll
    -0.07
    POSITIVE LOGITS
    empre
    0.07
    еш
    0.07
    amer
    0.07
     Rice
    0.07
     treeNode
    0.07
    走路
    0.06
    Real
    0.06
    าร
    0.06
     Agr
    0.06
    appro
    0.06
    Act Density 0.044%

    No Known Activations