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

    Neuronpedia

    INDEX
    Explanations

    C++ virtual functions/destructors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diminuir
    -0.09
    取得
    -0.08
    .ful
    -0.08
    Reduce
    -0.08
     fulfillment
    -0.07
     réduction
    -0.07
     jogos
    -0.07
     igen
    -0.07
    스로
    -0.07
    ไม่
    -0.07
    POSITIVE LOGITS
    (anchor
    0.09
     anchor
    0.09
    胖
    0.08
     rémun
    0.08
    anchor
    0.08
     രാഷ്ട്രീയ
    0.08
     വ്യക്തമ
    0.08
    -anchor
    0.08
     investeren
    0.08
     Anchor
    0.08
    Act Density 0.001%

    No Known Activations