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

    Neuronpedia

    INDEX
    Explanations

    known as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    moth
    -0.09
    ifen
    -0.09
     Barn
    -0.09
     dòng
    -0.08
    EFAULT
    -0.08
     cá»Ń
    -0.08
    еÑĤи
    -0.08
    entine
    -0.08
    getter
    -0.08
     cour
    -0.08
    POSITIVE LOGITS
    roud
    0.10
    464
    0.09
    eton
    0.09
     Craw
    0.09
     Toolbox
    0.08
    azzi
    0.08
    /pol
    0.08
    rega
    0.08
     Levi
    0.08
    âr
    0.08
    Act Density 0.259%

    No Known Activations