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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     কিংবা
    -0.10
     oswa
    -0.09
    handling
    -0.09
     অথবা
    -0.08
    刷水
    -0.08
     vagy
    -0.08
     both
    -0.08
    letes
    -0.08
     illetve
    -0.08
    购彩票
    -0.08
    POSITIVE LOGITS
     qualific
    0.08
     Sama
    0.07
     titular
    0.07
     wux
    0.07
     IDENT
    0.07
     eben
    0.07
     identical
    0.07
     ekte
    0.07
     této
    0.07
     kët
    0.07
    Act Density 0.271%

    No Known Activations