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
     Avenue
    -0.07
    iado
    -0.07
     Huntington
    -0.07
    dney
    -0.06
     Estate
    -0.06
     deletion
    -0.06
     councillor
    -0.06
     theo
    -0.06
     dateString
    -0.06
     TTL
    -0.06
    POSITIVE LOGITS
     sparks
    0.11
     spark
    0.10
     Sparks
    0.10
     Spark
    0.09
     sparked
    0.09
    Spark
    0.08
    spark
    0.08
     Ник
    0.07
     touched
    0.07
    works
    0.07
    Act Density 0.005%

    No Known Activations