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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     finance
    -0.07
    BBC
    -0.07
    (compare
    -0.07
    isten
    -0.07
    局势
    -0.07
    ddie
    -0.06
    .zz
    -0.06
    dio
    -0.06
     Italia
    -0.06
     mcc
    -0.06
    POSITIVE LOGITS
    HTML
    0.07
    Labels
    0.07
     Mart
    0.07
     הפר
    0.07
    chedulers
    0.07
    医护人员
    0.07
    Appending
    0.07
     elems
    0.07
    Ù
    0.07
    大きな
    0.07
    Act Density 0.023%

    No Known Activations