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

    Neuronpedia

    INDEX
    Explanations

    political contributions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mz
    -0.10
     ನೇ
    -0.09
     подбор
    -0.08
    .original
    -0.08
     guider
    -0.08
     cig
    -0.08
    ollows
    -0.08
    =item
    -0.08
     vznik
    -0.08
     llegará
    -0.08
    POSITIVE LOGITS
     simplistic
    0.08
     misconception
    0.07
     simplifying
    0.07
     banal
    0.07
     auditorium
    0.07
     minimizing
    0.07
    ા�
    0.07
    simpl
    0.07
     State
    0.07
     overlooked
    0.07
    Act Density 0.000%

    No Known Activations