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

    Neuronpedia

    INDEX
    Explanations

    spark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сло
    -0.07
     rely
    -0.06
     exporting
    -0.06
    these
    -0.06
     multin
    -0.06
     пере
    -0.06
    Від
    -0.06
     reassure
    -0.06
     rearr
    -0.06
     writes
    -0.06
    POSITIVE LOGITS
     sparked
    0.14
     sparking
    0.09
     Spark
    0.09
     sparks
    0.09
     Sparks
    0.09
     spark
    0.08
    -sync
    0.07
    0.07
     sparkle
    0.07
    `}
    0.06
    Act Density 0.007%

    No Known Activations