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

    Neuronpedia

    INDEX
    Explanations

    modern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confirm
    -0.08
     significant
    -0.08
     restore
    -0.07
     restores
    -0.07
     what
    -0.07
     restoring
    -0.07
     configuration
    -0.07
    confirm
    -0.07
     Restore
    -0.07
     установ
    -0.07
    POSITIVE LOGITS
    作品
    0.09
    Pacific
    0.09
     작품
    0.09
     XXI
    0.09
     thinkers
    0.09
     contemporain
    0.09
     abrasive
    0.08
    HOL
    0.08
     Haj
    0.08
     playwright
    0.08
    Act Density 0.007%

    No Known Activations