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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Neighbor
    -0.07
    _xs
    -0.06
     Sinh
    -0.06
    비스
    -0.06
     citizenship
    -0.06
     membership
    -0.06
     době
    -0.06
     gönder
    -0.06
    าจะ
    -0.06
     гром
    -0.06
    POSITIVE LOGITS
    pageTitle
    0.07
    	sort
    0.06
    �
    0.06
     Utils
    0.06
    LOY
    0.06
    citation
    0.06
     عاما
    0.06
    _supp
    0.06
    Meanwhile
    0.06
     "),
    0.06
    Act Density 0.563%

    No Known Activations