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

    Neuronpedia

    INDEX
    Explanations

    summary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    伙
    -0.09
     Spur
    -0.08
     gammel
    -0.08
    Puzzle
    -0.08
    ಹ
    -0.08
     thwart
    -0.07
     puzzle
    -0.07
    Music
    -0.07
     qho
    -0.07
     dents
    -0.07
    POSITIVE LOGITS
    summary
    0.15
     summary
    0.13
    _summary
    0.13
    (summary
    0.12
     summar
    0.12
    -summary
    0.12
    .summary
    0.12
     Summary
    0.12
     resumen
    0.11
     summarized
    0.11
    Act Density 0.041%

    No Known Activations